Article

Partially Supervised Spatiotemporal Clustering for Burglary Crime Series Identification

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Statistical clustering of criminal events can be used by crime analysts to create lists of potential suspects for an unsolved crime, to identify groups of crimes that may have been committed by the same individuals or group of individuals, for offender profiling and for predicting future events. We propose a Bayesian model-based clustering approach for criminal events. Our approach is semisupervised, because the offender is known for a subset of the events, and utilizes spatiotemporal crime locations as well as crime features describing the offender's modus operandi. The hierarchical model naturally handles complex features that are often seen in crime data, including missing data, interval-censored event times and a mix of discrete and continuous variables. In addition, our Bayesian model produces posterior clustering probabilities which allow analysts to act on model output only as warranted. We illustrate the approach by using a large data set of burglaries in 2009–2010 in Baltimore County, Maryland.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... For crime categories that involve serial offenders, i.e. where the same offender commits two or more crimes in the same category, law enforcement agencies strive to link crimes into series [1,2,3]. The linking of crimes enable investigators to get a more comprehensive understanding, based on the combined knowledge and evidence collected from the different crime scenes, compared to when investigating each crime in isolation [4]. ...
... The linking of crimes enable investigators to get a more comprehensive understanding, based on the combined knowledge and evidence collected from the different crime scenes, compared to when investigating each crime in isolation [4]. In addition, such linking also enable more efficient use of the police force's scarce resources than if investigating each crime individually [1]. ...
... Reich and Porter propose a Bayesian model-based clustering approach based on spatiotemporal and MO characteristics from 11, 524 US residential burglary crime scenes [1]. The proposed approach is semi-supervised because the offender is known for a subset of the burglaries. ...
Article
Objectives: The present study aims to extend current research on how offenders’ modus operandi (MO) can be used in crime linkage, by investigating the possibility to automatically estimate offenders’ risk exposure and level of pre-crime preparation for residential burglaries. Such estimations can assist law enforcement agencies when linking crimes into series and thus provide a more comprehensive understanding of offenders and targets, based on the combined knowledge and evidence collected from different crime scenes. Methods: Two criminal profilers manually rated offenders’ risk exposure and level of pre-crime preparation for 50 burglaries each. In an experiment we then analyzed to what extent 16 machine-learning algorithms could generalize both offenders’ risk exposure and preparation scores from the criminal profilers’ ratings onto 15,598 residential burglaries. All included burglaries contain structured and feature-rich crime descriptions which learning algorithms can use to generalize offenders’ risk and preparation scores from. Results: Two models created by Naïve Bayes-based algorithms showed best performance with an AUC of 0.79 and 0.77 for estimating offenders' risk and preparation scores respectively. These algorithms were significantly better than most, but not all, algorithms. Both scores showed promising distinctiveness between linked series, as well as consistency for crimes within series compared to randomly sampled crimes. Conclusions: Estimating offenders' risk exposure and pre-crime preparation can complement traditional MO characteristics in the crime linkage process. The estimations are also indicative to function for cross-category crimes that otherwise lack comparable MO. Future work could focus on increasing the number of manually rated offenses as well as fine-tuning the Naïve Bayes algorithm to increase its estimation performance. [A self-archived pre-print manuscript is available online. See comment below for the link. ]
... This leads, in general, to models that handle missing data under the Bayesian framework. Indeed, Reich and Porter (2015) adopted a Bayesian modeling framework for clustering criminal events which, among other features, enabled them to deal with interval-censored event times. Besides, the model proposed by these authors allowed them to link events that share the same modus operandi or offender (in case this information is available). ...
... The model implemented has allowed us to see how discarding temporally-uncertain observations in the analysis can lead to erroneous conclusions. Although this kind of modeling approach for dealing with interval-censored event observations has already been proposed in the literature (Reich and Porter 2015), this article has the novelty, to the best of the author's knowledge, of following the aoristic approach in a modeling context, while performing a complete comparison of the model proposed with the complete cases counterpart, which would be a typical choice. There is still room for improvement in the model proposed. ...
Article
Full-text available
Purpose Crime data analysis has gained significant interest due to its peculiarities. One key characteristic of property crimes is the uncertainty surrounding their exact temporal location, often limited to a time window. Methods This study introduces a spatio-temporal logistic regression model that addresses the challenges posed by temporal uncertainty in crime data analysis. Inspired by the aoristic method, our Bayesian approach allows for the inclusion of temporal uncertainty in the model. Results To demonstrate the effectiveness of our proposed model, we apply it to both simulated datasets and a dataset of residential burglaries recorded in Valencia, Spain. We compare our proposal with a complete cases model, which excludes temporally-uncertain events, and also with alternative models that rely on imputation procedures. Our model exhibits superior performance in terms of recovering the true underlying crime risk. Conclusions The proposed modeling framework effectively handles interval-censored temporal observations while incorporating covariate and space–time effects. This flexible model can be implemented to analyze crime data with uncertainty in temporal locations, providing valuable insights for crime prevention and law enforcement strategies.
... This leads, in general, to models that handle missing data under the Bayesian framework. Indeed, Reich and Porter (2015) adopted a Bayesian modeling framework for clustering criminal events which, among other features, allows for dealing with interval-censored event times. In this case, the authors treated interval-censored event times as latent variables with full conditional following a truncated normal distribution with mean equal to the cluster mean (that is, the average temporal location of the events belonging to the same cluster). ...
... The model implemented has allowed us to see how discarding temporally-uncertain observations in the analysis can lead to erroneous conclusions. Although this kind of modeling approach for dealing with interval-censored event observations has already been proposed in the literature (Reich and Porter, 2015), this article has the novelty, to the best of the author's knowledge, of following the aoristic approach in a modeling context, while performing a complete comparison of the model proposed with the complete cases counterpart, which would be a typical choice. ...
Preprint
From a statistical point of view, crime data present certain peculiarities that have led to a growing interest in their analysis. In particular, a characteristic that some property crimes frequently present is the existence of uncertainty about their exact location in time, being usual to only have a time window that delimits the occurrence of the event. There are different methods to deal with this type of interval-censored observation, most of them based on event time imputation. Another alternative is to carry out an aoristic analysis, which is based on assigning the same weight to each time unit included in the interval that limits the uncertainty about the event. However, this method has its limitations. In this paper, we present a spatio-temporal model based on the logistic regression that allows the analysis of crime data with temporal uncertainty, following the spirit of the aoristic method. The model is developed from a Bayesian perspective, which allows accommodating the temporal uncertainty of the observations. The model is applied to a dataset of residential burglaries recorded in Valencia, Spain. The results provided by this model are compared with those corresponding to the complete cases model, which discards temporally-uncertain events.
... For crime categories that involve serial offenders, i.e. where the offender commits two or more crimes of same type, law enforcement agencies strive to combine crimes committed by the same offender(s) into crime series [9] [16]. This allows investigators to get a more complete picture based on all information and evidence collected from the various crime scenes, compared to investigating each crime in isolation [18]. ...
... This allows investigators to get a more complete picture based on all information and evidence collected from the various crime scenes, compared to investigating each crime in isolation [18]. Also, the construction of crimes into series has proved to be more resource efficient than investigating each crime individually, given that the crimes in the series really are committed by the same offender(s) [16]. Linking crimes into series could be done based on physical evidence, e.g. ...
Conference Paper
Full-text available
Law enforcement agencies strive to link serial crimes, most preferably based on physical evidence, such as DNA or fingerprints, in order to solve criminal cases more efficiently. However, physical evidence is more common at crime scenes in some crime categories than others. For crime categories with relative low occurrence of physical evidence it could instead be possible to link related crimes using soft evidence based on the perpetrators' modus operandi (MO). However, crime linkage based on soft evidence is associated with considerably higher error-rates, i.e. crimes being incorrectly linked. In this study, we investigate the possibility of filtering erroneous crime links based on travel time between crimes using web-based direction services, more specifically Google maps. A filtering method has been designed, implemented and evaluated using two data sets of residential burglaries, one with known links between crimes, and one with estimated links based on soft evidence. The results show that the proposed route-based filtering method removed 79 % more erroneous crimes than the state-of-the-art method relying on Euclidean straight-line routes. Further, by analyzing travel times between crimes in known series it is indicated that burglars on average have up to 15 minutes for carrying out the actual burglary event.
... 2,[10][11][12][13][14] But research has also been conducted into clustering crime cases as a means of reducing the number of cases law enforcement o±cers have to analyze when looking for possible series of crimes. 5, 15 The clustering has been investigated for e.g., residential burglaries. Hotspot detection is a commonly used technique that can be used to group cases based on spatial information to, based on density, predict future crime locations. ...
... Initial research has investigated model-based clustering to combine di®erent aspects of crime data. 15 The performance of the cut-clustering algorithm investigated previously did not produce clustering solutions with a high accuracy. The choice of clustering algorithms a®ects the clustering solution and is dependent on the data investigated. ...
Article
Full-text available
To identify series of residential burglaries, detecting linked crimes performed by the same constellations of criminals is necessary. Comparison of crime reports today is difficult as crime reports traditionally have been written as unstructured text and often lack a common information-basis. Based on a novel process for collecting structured crime scene information, the present study investigates the use of clustering algorithms to group similar crime reports based on combined crime characteristics from the structured form. Clustering quality is measured using Connectivity and Silhouette index (SI), stability using Jaccard index, and accuracy is measured using Rand index (RI) and a Series Rand index (SRI). The performance of clustering using combined characteristics was compared with spatial characteristic. The results suggest that the combined characteristics perform better or similar to the spatial characteristic. In terms of practical significance, the presented clustering approach is capable of clustering cases using a broader decision basis.
... This could be used to generate a list of other crimes that a suspect may have committed for investigative or interrogative purposes. A variety of methods have been proposed for reactive linkage (e.g., Adderley, 2004;Adderley and Musgrove, 2003;Reich and Porter, 2014;Wang et al., 2013). The other approach, termed proactive linkage in Woodhams et al. (2007a) and what we refer to as crime series clustering, treats crime linkage as a clustering problem and attempts to cluster all of the crimes in a criminal database such that each identified cluster corresponds to a crime series. ...
... The other approach, termed proactive linkage in Woodhams et al. (2007a) and what we refer to as crime series clustering, treats crime linkage as a clustering problem and attempts to cluster all of the crimes in a criminal database such that each identified cluster corresponds to a crime series. A variety of clustering methods have been used to group similar crimes for further investigation or offender profiling (e.g., Adderley and Musgrove, 2001;Ma et al., 2010;Reich and Porter, 2014). ...
Article
Full-text available
The object of this paper is to develop a statistical approach to criminal linkage analysis that discovers and groups crime events that share a common offender and prioritizes suspects for further investigation. Bayes factors are used to describe the strength of evidence that two crimes are linked. Using concepts from agglomerative hierarchical clustering, the Bayes factors for crime pairs are combined to provide similarity measures for comparing two crime series. This facilitates crime series clustering, crime series identification, and suspect prioritization. The ability of our models to make correct linkages and predictions is demonstrated under a variety of real-world scenarios with a large number of solved and unsolved breaking and entering crimes. For example, a naive Bayes model for pairwise case linkage can identify 82% of actual linkages with a 5% false positive rate. For crime series identification, 74%-89% of the additional crimes in a crime series can be identified from a ranked list of 50 incidents.
... Instead, we propose the crimes identified during this process are used to support a process of crime linkage. Research (Reich and Porter, 2015) has shown that by examining just the spatiotemporal crime information and offender modus operandi, a serial crime series can be accurately identified. This is done through a process of a comparative case analysis (Burrell and Bull, 2011). ...
Article
Full-text available
This article describes how existing and newly emerged research can be combined to develop a more systematic model for responding to serial crimes. We believe that the model offers police services a more efficient and effective way to optimize the deployment and scheduling of police resources, and their associated activity, to combat serial offending. We suggest that the likely subsequent prevention and reduction of demand achieved will go some way to alleviate the impact of serial offending behavior. To develop our model, we draw upon criminological literature including theories of routine activity, rational choice, and situational crime prevention. By incorporating existing methods of hotspot identification, and combining these with processes to identify and respond to serial offending, we propose a six-stage, Dual Offender—Victim, Crime Prevention and Reduction model, that includes (1) crime linkage to identify serial offending; (2) near-repeat pattern analysis to identify the areas experiencing, and at immediate risk of victimization; (3) THE prediction of future, spatially displaced hotspots at high risk of victimization; (4) geographical profiling to identify the area of the likely home or base of the offender; (5) suspect mapping, ranking, targeting, and early intervention; and (6) tracking of spatial displacement, and offender management to maintain model effectiveness.
... Multiple linear regression analysis models the human perception of exceptional values. For criminal instances in which the culprit is determined for a subset of the occurrences, Reich and Porter [5] suggested a semi-supervised Bayesian model-based clustering methodology. It also made use of spatiotemporal crime locations as well as crime characteristics. ...
Article
Full-text available
Law enforcement agencies use various crime analysis tools. A large amount of crime data has enabled crime analysis. In this paper, the proposed research methodology uses Kernel Density Estimation (KDE) in a Geographical Information System (GIS) to analyze crime-type data. Bangalore and India newsfeeds are considered for experimental purposes. The paper introduces an optimized KDE machine learning algorithm that detects hotspots, estimates a location’s crime rate, and identifies point pattern lows and highs. As a result of the experiment, the proposed methodology identified that the bandwidth of the Geographical information system influences the visualization of crime density. The paper also aids in visually determining the appropriate bandwidth for the problem using an optimized KDE algorithm. We had identified a significant correlation between Newsfeed data and Official Government data, both overall Crime and by crime type. The proposed KDE model achieved a predictive performance of 77.49%.
... Crime linkage can be treated as a binary classification task with two classes denoting "serial crimes" and "nonserial crimes" [4] . Many classification algorithms have been applied and achieved excellent performance [5] . ...
Article
Crime linkage is a difficult task and is of great significance to maintaining social security. It can be treated as a binary classification problem. Some crimes are difficult to determine whether they are serial crimes under the existing evidence, so the two-way decisions are easy to make mistakes for some case pairs. Here, the three-way decisions based on the decision-theoretic rough set are applied and its key issue is to determine thresholds by setting appropriate loss functions. However, sometimes the loss functions are difficult to obtain. In this paper, a method to automatically learn thresholds of the three-way decisions without the need to preset explicit loss functions is proposed. We simplify the loss function matrix according to the characteristic of crime linkage, re-express thresholds by loss functions, and investigate the relationship between overall decision cost and the size of the boundary region. The trade-off between the uncertainty of the boundary region and the decision cost is taken as the optimization objective. We apply multiple traditional classification algorithms as base classifiers, and employ real-world cases and some public datasets to evaluate the effect of our proposed method. The results show that the proposed method can reduce classification errors.
... Thus, an analysis of the temporal and spatial distribution of burglaries, combined with the features that characterize and potentially discriminate these crimes, can provide an enriched description of offender whereabouts. This can have important policy implications in terms of possible proactive procedures for how to avoid crimes, as well as how the police force's scarce resources should be strategically and efficiently used [23]. ...
Article
Full-text available
The evidence that burglaries cluster spatio-temporally is strong. However, research is unclear on whether clustered burglaries (repeats/near-repeats) should be treated as qualitatively different crimes compared to spatio-temporally unrelated burglaries (non-repeats). This study, therefore, investigated if there were differences in modus operandi-signatures (MOs, the habits and methods employed by criminals) between near-repeat and non-repeat burglaries across 10 Swedish cities, as well as whether MO-signatures can aid in predicting if a burglary is classified as a near-repeat or a non-repeat crime. Data consisted of 5744 residential burglaries, with 137 MO features characterizing each case. Descriptive data of repeats/non-repeats is provided together with Wilcoxon tests of MO-differences between crime pairs, while logistic regressions were used to train models to predict if a crime scene was classified as a near-repeat or a non-repeat crime. Near-repeat crimes were rather stylized, showing heterogeneity in MOs across cities, but showing homogeneity within cities at the same time, as there were significant differences between near-repeat and non-repeat burglaries, including subgroups of features, such as differences in mode of entering, target selection, types of goods stolen, as well the traces that were left at the crime scene. Furthermore, using logistic regression models, it was possible to predict near-repeat and non-repeat crimes with a mean F1-score of 0.8155 (0.0866) based on the MO. Potential policy implications are discussed in terms of how data-driven procedures can facilitate analysis of spatio-temporal phenomena based on the MO-signatures of offenders, as well as how law enforcement agencies can provide differentiated advice and response when there is suspicion that a crime is part of a series as opposed to an isolated event.
... Bennell et al 2010a, b;Borg et al. 2014;Bouhana et al. 2016;Fox and Farrington 2014;Woodhams et al. 2019;Reich and Porter 2015;Salo et al. 2013;Tonkin 2012;Tonkin and Woodhams 2017;Turvey and Freeman 2016;Wang et al 2015 andZoete et al. 2015) and creation of a dedicated crime linkage international network (C-LINK, 2021). What a number of these previous studies have suggested is that contrary to what one might expect it is actually inter-crime distance, as opposed to the modus operandi of an offender(Bennell and Jones 2005: 23) which is the most accurate linkage feature, particularly when researching serious acquisitive crime such as burglaries and stealing from motor vehicles(Bennell and Jones 2005;Bennell and Canter 2002;Davies et al. 2012; Santtilla and Korpela et al. 2004;Tonkin et al 2008;Tonkin et al. 2008;. ...
Article
Full-text available
Crime linkage is a systematic way of assessing behavioural or physical characteristics of crimes and considering the likelihood they are linked to the same offender. This study builds on research in this area by replicating existing studies with a new type of burglar known as optimal foragers , who are offenders whose target selection is conducted in a similar fashion to foraging animals . Using crimes identified by police analysts as being committed by foragers this study examines their crime scene behaviour to assess the level of predictive accuracy for linking crimes based on their offending characteristics. Results support previous studies on randomly selected burglary offence data by identifying inter-crime distance as the highest linking indicator, followed by target selection, entry behaviour, property stolen and offender crime scene behaviour. Results discuss distinctions between this study and previous research findings, outlining the potential that foraging domestic burglary offenders display distinct behaviours to other forms of offender (random/marauder/commuter).
... Supervised methods treat serial crime detection as a binary classification task, and the methods used include neural networks [13], logistic regression [7,23,24], decision trees [25], and Bayesian classification [26], etc. Apart from these, various other approaches are also applied. Reich and Porter designed a semisupervised Bayesian model-based clustering algorithm to group similar crimes [27]. Some researchers have applied fuzzy multicriteria decision making(MCDM) to combine several attributes to aggregate a single value denoting the overall similarity between crimes [28,29]. ...
Article
Full-text available
Detecting serial crimes is to find criminals who have committed multiple crimes. A classification technique is often used to process serial crime detection, but the pairwise comparison of crimes is of quadratic complexity, and the number of nonserial case pairs far exceeds the number of serial case pairs. The blocking method can play a role in reducing pairwise calculation and eliminating nonserial case pairs. But the limitation of previous studies is that most of them use a single criterion to select blocks, which is difficult to guarantee an excellent blocking result. Some studies integrate multiple criteria into one comprehensive index. However, the performance is easily affected by the weighting method. In this paper, we propose a combined blocking (CB) approach. Each criminal behaviour is defined as a behaviour key (BHK) and used to form a block. CB learns several weak blocking schemes by different blocking criteria and then combines them to form the final blocking scheme. The final blocking scheme consists of several BHKs. Because rare behaviour can better identify crime series, each BHK is assigned a score according to its rarity. BHKs and their scores are used to determine whether a case pair need to be compared. After comparing with multiple blocking methods, CB can effectively guarantee the number of serial case pairs while greatly reducing unnecessary nonserial case pairs. The CB is embedded in a supervised machine learning framework. Experiments on real-world robbery cases demonstrate that it can effectively reduce pairwise comparison, alleviate the class imbalance problem and improve detection performance.
... For example (Dagher & Fung, 2013) have introduced subject-based semantic document clustering algorithm employing vector space model to groups documents into a set of overlapping clusters, each corresponding to one unique subject. (Reich & Porter, 2015) proposed a Bayesian model, utilizing crime locations and offender's modus operandi as fixed feature vector for burglary crime series identifications. Borg, Boldt, Lavesson, Melander, and Boeva, (2014), demonstrated minimum cut based graph clustering to detect residential burglaries series. ...
... Moreover, spatio-temporal clustering can also serve as an important pre-process step for other spatio-temporal data mining techniques (Deng, Yang, & Liu, 2018). Currently, spatio-temporal clustering is widely applied in crime behavior prediction, climate change analysis, epidemic outbreak detection, traffic dynamic modeling, earthquake research, and so on (Eckley & Curtin, 2012;Georgoulas et al., 2013;Kulldorff, Heffernan, Hartman, Assunçãco, & Mostashari, 2005;Reich & Porter, 2015;Wu, Zurita-Milla, & Kraak, 2016). ...
... klassificeringsalgoritmer) på de brott som man vet har utförts av en viss gärningsman genom länkning baserat på fingeravtryck eller DNA. Därefter kan klassificeringsalgoritmerna prediktera vilka av alla andra brott som är mest sannolika att höra till respektive serie, baserat på likheter i deras modus operandi (Reich & Porter, 2015) (Yokota & Watanabe, 2002). Inget av detta skulle vara möjligt att göra på lika hög detaljnivå med textbaserade RAR-anmälningar. ...
Article
Full-text available
Abstrakt Denna artikel utvärderar en strukturerad metod för registrering av brottsplatsuppgifter från mängd-/vardagsbrott genom en jämförelse med traditionella textbaserade brottsanmälningar. En initial användarstudie kopplad till ett bostadsinbrott utvärderar effektiviteten hos de båda metoderna. Effektiviteten kvantifieras som dels tiden det tar att registrera bostadsinbrottet samt antalet relevanta brottsplatsuppgifter som registreras. Resultaten visar att den strukturerade metoden har statistiskt signifikant snabbare avrapportering än traditionella textbaserade anmälningar (p
... klassificeringsalgoritmer) på de brott som man vet har utförts av en viss gärningsman genom länkning baserat på fingeravtryck eller DNA. Därefter kan klassificeringsalgoritmerna prediktera vilka av alla andra brott som är mest sannolika att höra till respektive serie, baserat på hur lika de är i sitt modus operandi (Reich & Porter, 2015) (Yokota & Watanabe, 2002). Inget av detta skulle vara möjligt att göra på lika hög detaljnivå med textbaserade RAR-anmälningar. ...
Article
Full-text available
This work evaluates a novel structured method for reporting crime and registering crime scene data by comparing the method with traditional text-based crime reports. Swedish law enforcement officers were asked to register a residential burglary using both methods in order to measure the effectiveness of each method. The effectiveness was quantified as both the time it took to register the crime as well as the number of relevant unique crime scene details that were collected. The results show the structured method to be significantly more efficient than traditional text-based crime reports (p < 0.05). Also, the novel method registers 2.96 times more relevant and unique crime scene details on average. In addition to the differences in efficiency this work also discusses more qualitative pros and cons with the novel method, as well as various data analysis methods that could be used on the registered data. It is concluded that the novel method can benefit law enforcement agencies in two ways. First, related to increased quality and more elaborate crime reports. Secondly, related to significant time-savings, which according to a rough estimate is expect to lie in the range 11-30 full-time positions per year for Swedish law enforcement agencies, particularly for volume crime categories. Those resources could instead be used for unburden the workload for our law enforcement officers, and to some extent free resources that could be used in other parts of the organization. Note: this pre-print manuscript is written in Swedish. URL: https://arxiv.org/ftp/arxiv/papers/1709/1709.03581.pdf
... Results showed that their method had a better performance than traditional cluster methods such as hierarchical agglomerative clustering. A variety of other crime series detection method have been used to group similar crimes for further investigation or offender profiling [6,30,37,44,45] . Apart from the above-mentioned case pair classifying approach and serial crimes clustering approach, there were some other researches about serial crime linkage in the literature. ...
Article
Serial crimes pose a great threat to public security. Linking crimes committed by the same offender can assist the detecting of serial crimes and is of great importance in maintaining public security. Currently, most crime analysts still link serial crimes empirically especially in China and desire quantitative tools to help them. This paper presents a decision support system for crime linkage based on various, including behavioral, features of criminal cases. Its underlying technique is pairwise classification based on similarity, which is interpretable and easy to tune. We design feature similarity algorithms to calculate the pairwise similarities and build up a classifier to determine whether a case pair should belong to a series. A comprehensive case study of a real-world robbery dataset demonstrates its promising performance even with the default setting. This system has been deployed in a public security bureau of China and running for more than one year with positive feedback from users. The use of this system would provide individual officers with strong support in crimes investigation then allow law enforcement agency to save resources, since the system not only can link serial crimes automatically based on a classification model learned from historical crime data, but also has flexibility in training data update and domain experts interaction, including adjusting the key components like similarity matrices and decision thresholds to reach a good tradeoff between caseload and number of true linked pairs.
... In the last type of approach, crime series clustering, all the clusters are found simultaneously. 8,[27][28][29][30][31][32][33][34][35] One of the earliest approaches we know of for clustering crimes is that of Dahbur and Muscarello, 29 who used a neural network approach. (This method had some serious flaws that required extensive heuristic post-processing after the clusters were created, but aimed at solving the more general problem of crime clustering.) ...
Article
Full-text available
One of the most challenging problems facing crime analysts is that of identifying crime series, which are sets of crimes committed by the same individual or group. Detecting crime series can be an important step in predictive policing, as knowledge of a pattern can be of paramount importance toward finding the offenders or stopping the pattern. Currently, crime analysts detect crime series manually; our goal is to assist them by providing automated tools for discovering crime series from within a database of crimes. Our approach relies on a key hypothesis that each crime series possesses at least one core of crimes that are very similar to each other, which can be used to characterize the modus operandi (M.O.) of the criminal. Based on this assumption, as long as we find all of the cores in the database, we have found a piece of each crime series. We propose a subspace clustering method, where the subspace is the M.O. of the series. The method has three steps: We first construct a similarity graph to link crimes that are generally similar, second we find cores of crime using an integer linear programming approach, and third we construct the rest of the crime series by merging cores to form the full crime series. To judge whether a set of crimes is indeed a core, we consider both pattern-general similarity, which can be learned from past crime series, and pattern-specific similarity, which is specific to the M.O. of the series and cannot be learned. Our method can be used for general pattern detection beyond crime series detection, as cores exist for patterns in many domains.
Article
Full-text available
Objectives We illustrate how a machine learning algorithm, Random Forests, can provide accurate long-term predictions of crime at micro places relative to other popular techniques. We also show how recent advances in model summaries can help to open the ‘black box’ of Random Forests, considerably improving their interpretability.Methods We generate long-term crime forecasts for robberies in Dallas at 200 by 200 feet grid cells that allow spatially varying associations of crime generators and demographic factors across the study area. We then show how using interpretable model summaries facilitate understanding the model’s inner workings.ResultsWe find that Random Forests greatly outperform Risk Terrain Models and Kernel Density Estimation in terms of forecasting future crimes using different measures of predictive accuracy, but only slightly outperform using prior counts of crime. We find different factors that predict crime are highly non-linear and vary over space.Conclusions We show how using black-box machine learning models can provide accurate micro placed based crime predictions, but still be interpreted in a manner that fosters understanding of why a place is predicted to be risky.
Chapter
Full-text available
Police and law enforcement agencies perform social media analysis to gain a better understanding of criminal social networks structures and to identify potential criminal activities. The use of data mining techniques in social media analysis, however, faces issues and challenges such as linkage-based structural analysis, association extraction, community or group detection, behaviour and mood analysis, sentiment analysis and dynamic analysis of streaming networks. This chapter describes the extension of our developed framework and propose an association model for extracting multilevel associations based on associative questioning. We also describe data mining techniques used to visualize these associations through a 2D crime cluster space. The developed framework provides a complete data analytic solution towards identifying and understanding associations between crime entities and thus expedites the crime matching process.
Article
Studying crime trends and tendencies is an important problem that helps to identify socioeconomic patterns and relationships of crucial significance. Finite mixture models are famous for their flexibility in modeling heterogeneity in data. A novel approach designed for accounting for skewness in the distributions of matrix observations is proposed and applied to the United States crime data collected between 2000 and 2012 years. Then, the model is further extended by incorporating explanatory variables. A step-by-step model development demonstrates differences and improvements associated with every stage of the process. Results obtained by the final model are illustrated and thoroughly discussed. Multiple interesting conclusions have been drawn based on the developed model and obtained model-based clustering partition.
Article
Full-text available
Much previous research on behavioural case linkage has used binary logistic regression to build predictive models that can discriminate between linked and unlinked offences. However, classification tree analysis has recently been proposed as a potential alternative owing to its ability to build user‐friendly and transparent predictive models. Building on previous research, the current study compares the relative ability of logistic regression analysis and classification tree analysis to construct predictive models for the purposes of case linkage. Two samples are utilised in this study: a sample of 376 serial car thefts committed in the UK and a sample of 160 serial residential burglaries committed in Finland. In both datasets, logistic regression and classification tree models achieve comparable levels of discrimination accuracy, but the classification tree models demonstrate problems in terms of reliability or usability that the logistic regression models do not. These findings suggest that future research is needed before classification tree analysis can be considered a viable alternative to logistic regression in behavioural case linkage. Copyright © 2012 John Wiley & Sons, Ltd.
Article
Full-text available
In the absence of forensic evidence (such as DNA or fingerprints), offender behavior can be used to identify crimes that have been committed by the same person (referred to as behavioral case linkage). The current study presents the first empirical test of whether it is possible to link different types of crime using simple aspects of offender behavior. The discrimination accuracy of the kilometer distance between offense locations (the intercrime distance) and the number of days between offenses (temporal proximity) was examined across a range of crimes, including violent, sexual, and property-related offenses. Both the intercrime distance and temporal proximity were able to achieve statistically significant levels of discrimination accuracy that were comparable across and within crime types and categories. The theoretical and practical implications of these findings are discussed and recommendations made for future research.
Article
Full-text available
This article looks at the application of data-mining techniques, principally the multi-layer perceptron, radial basis function and self-organising map, to the recognition of burglary offences committed by a network of offenders. The aim is to suggest a list of currently undetected crimes that may be attributed to one or more members of the network and improve on the time taken to complete the task manually and the relevancy of the list of crimes. The data were drawn from four years of burglary offences committed within an area of the West Midlands police. They were encoded from text by a small team of specialists working to a well-defined protocol and analysed using the above techniques contained within the data-mining workbench of SPSS/Clementine. Within minutes, three months of undetected crimes were analysed through the Clementine stream, producing a list of offences that might be attributed to the network of offenders. The results were analysed by two police sergeants not associated with the development process who determined that 85 per cent of the nominated crimes could be attributed to the network of offenders. To produce a manual list would take between one-and-a-half and two hours and be between 5 per cent and 10 per cent accurate.
Article
Full-text available
The effectiveness, in prioritizing suspects, of six geographical profiling methods are compared by determining the rank to which each of 92 prolific burglars was assigned, from the total of 400 known burglars, who were selected from a large metropolitan database because they resided in the borough in which the crimes occurred. Using mean and median ranked prioritization of actual offenders, as well as the percentages that appeared in the top 5% of rankings and the area under the curve of a specially developed 'Ranked Prioritization Function,' RP(f), it was found that Dragnet using a logarithmic decay function and the distance from the centre of gravity produced the lowest average ranks, with 72% of the actual offenders in the top 5% of prioritized rankings. The implications of the findings are discussed.
Article
Full-text available
The present study aimed to identify dimensions of variation in serial homicide and to use these dimensions to behaviourally link offences committed by the same offender with each other. The sample consisted of 116 Italian homicides committed by 23 individual offenders. Each offender had committed at least two homicides. As some offenders had worked together and some murders involved more than one victim, there were 155 unique pairings of offenders and victims. Dichotomous variables reflecting crime features and victim characteristics were coded for each case. Using Mokken scaling, a nonparametric alternative to factor analysis, seven dimensions of variation were identified. Five of the dimensions described variations in the motivation for the killings. Three of these were concerned with aspects of instrumental motivation whereas two of the motivational scales described variations in sexual motivation. The two remaining dimensions dealt with the level of planning evident in the crime scene behaviour of the offender. Two dimensions were identified: one consisting of behaviours suggesting a higher level of control and another describing impulsiveness. Using discriminant function analysis with the dimensions as independent variables and the series an offence belonged to as dependent variable, 62.9% of the cases could be correctly assigned to the right series (chance expectation was 6.2%). The implications of the results for serial homicide investigations are discussed.
Article
Full-text available
Purpose . This paper is concerned with case linkage, a form of behavioural analysis used to identify crimes committed by the same offender, through their behavioural similarity. Whilst widely practised, relatively little has been published on the process of linking crimes. This review aims to draw together diverse published studies by outlining what the process involves, critically examining its underlying psychological assumptions and reviewing the empirical research conducted on its viability. Methods . Literature searches were completed on the electronic databases, PsychInfo and Criminal Justice Abstracts, to identify theoretical and empirical papers relating to the practice of linking crimes and to behavioural consistency. Results . The available research gives some support to the assumption of consistency in criminals' behaviour. It also suggests that in comparison with intra‐individual variation in behaviour, inter‐individual variation is sufficient for the offences of one offender to be distinguished from those of other offenders. Thus, the two fundamental assumptions underlying the practice of linking crimes, behavioural consistency and inter‐individual variation, are supported. However, not all behaviours show the same degree of consistency, with behaviours that are less situation‐dependent, and hence more offender‐initiated, showing greater consistency. Conclusions . The limited research regarding linking offenders' crimes appears promising at both a theoretical and an empirical level. There is a clear need, however, for replication studies and for research with various types of crime.
Article
Full-text available
The purpose of this study is to determine if readily available information about commercial and residential serial burglaries, in the form of the offender's modus operandi, provides a statistically significant basis for accurately linking crimes committed by the same offender. Logistic regression analysis is applied to examine the degree to which various linking features can be used to discriminate between linked and unlinked burglaries. Receiver operating characteristic (ROC) analysis is then performed to calibrate the validity of these features and to identify optimal decision thresholds for linking purposes. Contrary to crime scene behaviours traditionally examined to link serial burglaries, the distance between crime site locations demonstrated significantly greater effectiveness as a linking feature for both commercial and residential burglaries. Specifically, shorter distances between crimes signalled an increased likelihood that burglaries were linked. Thus, these results indicate that, if one examines suitable behavioural domains, high levels of stability and distinctiveness exist in the actions of serial burglars, and these actions can be used to accurately link crimes committed by the same offender. Copyright © 2005 John Wiley & Sons, Ltd.
Article
Full-text available
Purpose. Through an examination of serial rape data, the current article presents arguments supporting the use of receiver operating characteristic (ROC) analysis over traditional methods in addressing challenges that arise when attempting to link serial crimes. Primarily, these arguments centre on the fact that traditional linking methods do not take into account how linking accuracy will vary as a function of the threshold used for determining when two crimes are similar enough to be considered linked. Methods. Considered for analysis were 27 crime scene behaviours exhibited in 126 rapes, which were committed by 42 perpetrators. Similarity scores were derived for every possible crime pair in the sample. These measures of similarity were then subjected to ROC analysis in order to (1) determine threshold‐independent measures of linking accuracy and (2) set appropriate decision thresholds for linking purposes. Results. By providing a measure of linking accuracy that is not biased by threshold placement, the analysis confirmed that it is possible to link crimes at a level that significantly exceeds chance ( AUC = .75). The use of ROC analysis also allowed for the identification of decision thresholds that resulted in the desired balance between various linking outcomes (e.g. hits and false alarms). Conclusions. ROC analysis is exclusive in its ability to circumvent the limitations of threshold‐specific results yielded from traditional approaches to linkage analysis. Moreover, results of the current analysis provide a basis for challenging common assumptions underlying the linking task.
Article
Full-text available
The spatial analysis of crime and the current focus on hotspots has pushed the area of crime mapping to the fore, especially in regard to high volume offenses such as vehicle theft and burglary. Hotspots also have a temporal component, yet police recorded crime databases rarely record the actual time of offense as this is seldom known. Police crime data tends, more often than not, to reflect the routine activities of the victims rather than the offense patterns of the offenders. This paper demonstrates a technique that uses police START and END crime times to generate a crime occurrence probability at any given time that can be mapped or visualized graphically. A study in the eastern suburbs of Sydney, Australia, demonstrates that crime hotspots with a geographical proximity can have distinctly different temporal patterns.
Article
Full-text available
Case linkage involves identifying crime series on the basis of behavioral similarity and distinctiveness. Research regarding the behavioral consistency of serial rapists has accumulated; however, it has its limitations. One of these limitations is that convicted or solved crime series are exclusively sampled whereas, in practice, case linkage is applied to unsolved crimes. Further, concerns have been raised that previous studies might have reported inflated estimates of case linkage effectiveness due to sampling series that were first identified based on similar modus operandi (MO), thereby overestimating the degree of consistency and distinctiveness that would exist in naturalistic settings. We present the first study to overcome these limitations; we tested the assumptions of case linkage with a sample containing 1) offenses that remain unsolved, and 2) crime series that were first identified as possible series through DNA matches, rather than similar MO. Twenty-two series consisting of 119 rapes from South Africa were used to create a dataset of 7021 crime pairs. Comparisons of crime pairs that were linked using MO vs. DNA revealed significant, but small differences in behavioral similarity with MO-linked crimes being characterized by greater similarity. When combining these two types of crimes together, linked pairs (those committed by the same serial offender) were significantly more similar in MO behavior than unlinked pairs (those committed by two different offenders) and could be differentiated from them. These findings support the underlying assumptions of case linkage. Additional factors thought to impact on linkage accuracy were also investigated. KeywordsComparative case analysis–Linkage analysis–Behavioral linking–Sexual assault–Sexual offense
Conference Paper
Full-text available
This paper looks at the use of a Self Organizing Map (SOM), to link of records of crimes of serious sexual attacks. Once linked a profile can be derived of the offender(s) responsible.The data was drawn from the major crimes database at the National Crime Faculty of the National Police Staff College Bramshill UK. The data was encoded from text by a small team of specialists working to a well-defined protocol. The encoded data was analyzed using SOMs. Two exercises were conducted. These resulted in the linking of several offences in to clusters each of which were sufficiently similar to have possibly been committed by the same offender(s). A number of clusters were used to form profiles of offenders. Some of these profiles were confirmed by independent analysts as either belonging to known offenders or appeared sufficiently interesting to warrant further investigation.The prototype was developed over 10 weeks. This contrasts with an in-house study using a conventional approach, which took 2 years to reach similar results. As a consequence of this study the NCF intends to pursue an in-depth follow up study.
Conference Paper
Full-text available
The information explosion has led to problems and possibilities in many areas of society, including that of law enforcement. In comparing individual criminal investigations on similarity, we seize one of the opportunities of the information surplus to determine what crimes may or may not have been committed by the same group of individuals. For this purpose we introduce a new distance measure that is specifically suited to the comparison between investigations that differ largely in terms of available intelligence. It employs an adaptation of the probability density function of the normal distribution to constitute this distance between all possible couples of investigations. We embed this distance measure in a four-step paradigm that extracts entities from a collection of documents and use it to transform a high dimensional vector table into input for a police operable tool. The eventual report is a two-dimensional representation of the distances between the various investigations and will assist the police force on the job to get a clearer picture of the current situation.
Conference Paper
Full-text available
This paper looks at the application of data mining techniques, principally the Self Organising Map, to the recognition of burglary offences committed by an offender who, although part of a small network, appears to work on his own. The aim is to suggest a list of currently undetected crimes that may be attributed to him, improve on the time taken to complete the task manually and the relevancy of the list of crimes. The data was drawn from one year of burglary offences committed within the West Midlands Police area, encoded from text and analysed using techniques contained within the data mining workbench of SPSS/Clementine. The undetected crimes were analysed to produce a list of offences that may be attributed to the offender.
Article
Full-text available
Temporal limitations of GIS databases are never more apparent than when the time of a change to any spatial object is unknown.This paper examines an unusual type of spatiotemporalimprecisionwhere an event occurs at a known location but at an unknowntime.Aoristic analysis can provide a temporalweight and give an indication of the probability that the event occurred within a deéned period. Visualisation of temporal weights can be enhanced by modiécations to existing surface generation algorithms and a temporal intensity surface can be created. An example from burglaries in Central Nottingham (UK) shows that aoristic analysis can smooth irregularities arising from poor database interroga- tion, and provide an alternative conceptualisation of space and time that is both comprehensible and meaningful.
Article
Full-text available
The present study investigated the possibility of statistically linking arson cases based on consistency of behaviors from one crime scene to another. Serial and spree arson cases were studied to differentiate underlying themes and to link cases committed by the same offender. The material consisted of 248 arson cases which formed 42 series of arsons. A content analysis using 45 dichotomous variables was carried out and principal components (PCA) analysis was performed to identify underlying themes. Summary scores reflecting the themes were calculated. Linking effectiveness was tested with a discriminant analysis using the summary scores. The PCA analysis was successful and underlying themes which were in accordance with previous studies could be identified. Six factors were retained, in the PCA. The linking of the arson cases was possible to a satisfactory level: 33% of the cases could be correctly linked and for over 50% of the cases, the series they actually belonged to was among the ten series identified as most probable on the basis of the linking analysis. From a practical point of view, the results could be used as a basis for developing support systems for police investigations of arson. © Copyright Springer, 2004
Article
Full-text available
Bibliography: p. [285]-299 Includes index
Article
Full-text available
Case linkage, the identification of crimes suspected of being committed by the same perpetrator on the basis of behavioral similarity, and offender profiling, the inference of offender characteristics from offense behaviors, are used to advise police investigations and, in relation to case linkage, have been admitted in legal proceedings. Criteria for expert evidence, such as the Daubert criteria (Daubert v. Merrell Dow Pharmaceuticals, 1993), place stringent conditions on the admissibility of expert evidence. The future contribution of these practices to legal proceedings depends, in part, on whether they are underpinned by hypotheses that are testable and supported. The 3 hypotheses of offender behavioral consistency, of offender behavioral distinctiveness, and of a homology (direct relationship) between offender characteristics and behavior were empirically examined using a sample of serial commercial robberies. Support was found for the former 2 hypotheses but not for the last. The findings of the 2 studies have implications for the future development of these practices, for legal practitioners evaluating expert evidence, and for the implementation of public policy.
Article
Full-text available
This paper uses statistical models to test directly the police practice of utilising modus operandi to link crimes to a common offender. Data from 86 solved commercial burglaries committed by 43 offenders are analysed using logistic regression analysis to identify behavioural features that reliably distinguish between linked and unlinked crime pairs. Receiver operating characteristic analysis is then used to assign each behavioural feature an overall level of predictive accuracy. The results indicate that certain features, in particular the distances between burglary locations, lead to high levels of predictive accuracy. This study therefore reveals some of the important consistencies in commercial burglary behaviour. These have theoretical value in helping to explain criminal activity. They also have practical value by providing the basis for a diagnostic tool that could be used in comparative case analysis.
Article
This report presents the development and evaluation of the suspect retrieval system based on modus operandi developed by the National Research Institute of Police Science in Japan. The database used in the system stores a large number of records consisting of the modus operandi of prior offenders. A score is assigned to each record, where each score represents the similarity of the modus operandi between each record and a crime under investigation. The similarity is statistically calculated based on the choice probability of each modus operandi. Suspects in the database are rank ordered according to scores. The higher a rank is, the more likely a suspect is expected to have committed the crime under investigation. The validity of the system is evaluated with data about Japanese burglars (n = 12,468) and some factors influencing the accuracy of the retrieval are discussed.
Article
Purpose. The study extends research by Santtila et al. (2008) by investigating the effectiveness of linking cases of serial homicide using behavioural patterns of offenders, analysed through Bayesian reasoning. The study also investigates the informative value of individual behavioural variables in the linking process. Methods. Offender behaviour was coded from official documents relating to 116 solved homicide cases belonging to 19 separate series. The basis of the linkage analyses was 92 behaviours coded as present or absent in the case based on investigator observations on the crime scene. We developed a Bayesian method for linking crime cases and judged its accuracy using cross‐validation. We explored the information added by individual behavioural variables, first, by testing if the variable represented purely noise with respect to classification, and second, by excluding variables from the original model, one by one, by choosing the behaviour that had the smallest effect on classification accuracy. Results. The model achieved a classification accuracy of 83.6% whereas chance expectancy was 5.3%. In simulated scenarios of only one and two known cases in a series, the accuracy was 59.0 and 69.2%, respectively. No behavioural variable represented pure noise but the same level of accuracy was achieved by analysing a set of 15, as analysing all 92 variables. Conclusion. The study illustrates the utility of analysing individual behavioural variables through Bayesian reasoning for crime linking. Feasible applied use of the approach is illustrated by the effectiveness of analysing a small set of carefully chosen variables.
Article
Finding similar crime case subsets is an important task for intelligence analysts in crime investigation. It can not only provide multiple clues to solve crimes but also improve efficiency to catch the criminals. However, the conventional approach by querying specific attributes in relational databases has two defects: first, it is relatively of poor efficiency when a lot of incidents have to be handled; second, the querying process can not reflect the importance of attributes in different case categories. In this paper, we propose a two-phase clustering algorithm called AK-Modes to automatically find the similar case subsets from large datasets. In the attribute-weighing phase, we compute the weight of each attribute related to an offender's behavior trait using the concept Information Gain Ratio (IGR) in classification domain. Then the result of attribute-weighing phase is utilized in the clustering process to find the similar case subsets. Experiments show that AK-Modes is effective and can find significant results.
Article
This paper discusses the development of a filter model for prioritizing possible links in dwelling burglary. The filters utilize the central aspects of crime scene information that is available and accessible to investigators in burglary, namely geo-spatial, temporal, behavioural, and dwelling information. The proposed filters were analysed using a sample of 215 dwelling burglaries committed by 43 serial burglars (i.e. 5 offences each) in order to determine the sequence in which the filters should be considered in prioritizing possible linked offences. The results indicated that the following order (i.e. better performance to worse performance) was most effective at linking offences, utilizing: (1) geo-spatial information, (2) temporal aspects, (3) behavioural information and, lastly, (4) dwelling characteristics. Specifically, the results indicated that offences in close proximity to one another should be given priority. Further, any offence occurring within a 28-day span before or after the index offence should be given priority. The paper argues that behavioural and dwelling characteristics are less effective for linking than geo-spatial and temporal information because the former two aspects are influenced significantly by situational and contextual cues on offender decision-making.
Article
’Hard’ forensic evidence (eg DNA) may be the best means of linking crimes, but it is often absent at burglary crime scenes. Modus operandi information is always present to some degree, but little is known of its significance in matching burglaries. This paper evaluates the ability of three algorithms to match a target crime to the actual offender within a database of 966 offences. The first (RCPA) uses only MO information, the second (RPAL) only temporal and geographic data and a third (COMBIN) is a combination of the two. A score of one indicates a perfect match between the target crime and the case selected by the algorithm. The lowest possible rank is 965 showing that 965 cases were selected before the target offence. The RPAL and COMBIN each achieve a perfect match for 24 per cent of the crimes and succeed in matching over half of the crimes at a score of 10 or less. For prolific offenders, using MO information alone is better than temporal and geographic data, although the best performance is achieved when in combination. Behavioural, spatial and temporal information is collected by many Police Services. The value and means of utilising such data in linking crimes is clearly demonstrated.
Article
This paper considers a suspect prioritization technique and tests its validity using a sample of commercial armed robbery offences from St John's, Newfoundland, Canada. The proposed technique is empirically grounded in criminal careers and journey‐to‐crime research. Suspects with a previous criminal history are selected and ranked in ascending order by the distance they live from the location of the crime in question, with the nearest suspect given highest priority. Effectiveness is measured by the percentage of ranked suspects that needs to be searched before the offender is identified. Results show that 65% of the robbers were identified in the top 10% of ranked suspects. Limitations and proposed refinements are discussed in terms of future prioritization strategies and policing research.
Article
We consider the problem of determining the structure of clustered data, without prior knowledge of the number of clusters or any other information about their composition. Data are represented by a mixture model in which each component corresponds to a different cluster. Models with varying geometric properties are obtained through Gaussian components with different parameterizations and cross-cluster constraints. Noise and outliers can be modeled by adding a Poisson process component. Partitions are determined by the EM (expectation-maximization) algorithm for maximum likelihood, with initial values from agglomerative hierarchical clustering. Models are compared using an approximation to the Bayes factor based on the Bayesian Information Criterion (BIC); unlike significance tests, this allows comparison of more than two models at the same time, and removes the restriction that the models compared be nested. The problems of determining the number of clusters and the clustering method are solved simultaneously by choosing the best model. Moreover, the EM result provides a measure of uncertainty about the associated classification of each data point.
Article
In daylight, burglars minimized the risks of being spotted by selecting “up-market” targets with better front cover and low occupancy that reflected the occupants' higher employment levels. After dark, townhouses with less cover were popular despite victims, fewer of whom were employed, raising more alerts. Evidence indicates consistency with routine activity theory, and target strategies appear rational, though shaped by differences in risks and offenders. Lifestyles and routine activities of victims, coupled with daylight and darkness changes, created burglary opportunities. Distinctive daylight and darkness strategies proved attractive to certain types of offenders, so that housing morphology, victims, their lifestyle, risks, rewards and burglar characteristics were distinctively aligned, providing the framework for target and area selection. Theories need to incorporate contrasts in daylight-darkness and housing morphologies, and relate to offender diversity.
Article
A sample of serial stranger rape cases ( n = 43) that had occurred in Finland during the years 1983–2001 were studied with the objectives being to: (a) describe the characteristics of the offenders; (b) explore the structure of serial rape; and (c) demonstrate behavioural linkage through an analysis of the offenders' crime scene behaviour using both multidimensional scaling (MDS) and discriminant function analysis (DFA). The material was content analysed with regard to the occurrence of a number of dichotomous variables. The inter-relationships of the variables was studied using MDS. The analysis revealed two previously identified major modes of interaction with the victim: involvement and hostility. Employing MDS and DFA, it was shown that the offences of different offenders were distinguishable in terms of variation between the offences of different offenders and consistency within the offences of a single offender. Using DFA, the classification accuracy clearly exceeds that expected by chance, and 25.6% of the cases were classified without any error. The results are discussed in relation to their practical utility and previous studies. Copyright © 2005 John Wiley & Sons, Ltd.
Article
The origins of ‘Offender Profiling’ in the advice given by police medical advisors and other experts to criminal investigations are briefly outlined. The spread of such advice to police enquiries across the United States in the early 1970s, culminating in its uptake by Special Agents of the FBI in the mid‐1970s and the widespread promotion of their services through the fictional writings of Thomas Harris and others is noted. The development beyond the early application to serial killer investigations, and the focus on psychopathological explanations, to cover the full gamut of crime from, for instance, arson and burglary to terrorism, is briefly reviewed. The consideration of the social psychological processes inherent in criminality as well as the characteristics of individual offenders also broadens out the concerns of the field. The linking of crimes to a common offender as well as predicting their future actions further widens the range of issues to be dealt with. The many psychological and practical questions raised by these ‘profiling’ activities are summarised. These include questions of inference and prediction, about criminals and their crimes, both about their characteristics and about the spatial patterns of their activities. Related topics concerning the sources of information for both investigators and research are also summarised. These cover the full range from interviewing witnesses to the management of informants. The complexity of information management and inference derivation points to the need to understand investigative decision‐making and how it can be supported. These other issues, beyond those inherent in ‘profiling’, such as data integrity and investigative decision support, taken with the central ‘profiling’ questions leads to the identification of a new domain of applied psychology, ‘Investigative Psychology’. It is argued that the core topic of this domain, as in any emerging science, is how to appropriately describe and classify the central matters under consideration, i.e. criminals and their activities. The difficulties in setting up reliable, robust and valid classification schemes are discussed and approaches to overcoming these difficulties considered. It is emphasised that although many researchers have found Multi‐Dimensional Scaling procedures to be productive they are only one of many fruitful sets of approaches that are possible. The increasing variety of areas, for which Investigative Psychology is relevant, from tax evasion to peace keeping, and from evidence in court to organisational threat management, is briefly reviewed. In conclusion it is noted that Investigative Psychology can be considered as a general approach to problem solving relevant far beyond criminal investigations. This new Journal of Investigative Psychology and Offender Profiling therefore has rich and wide‐ranging potential. Copyright © 2004 John Wiley & Sons, Ltd.
Article
Whilst case linkage is used with serious forms of serial crime (e.g. rape and murder), the potential exists for it to be used with volume crime. This study replicates and extends previous research on the behavioural linking of burglaries. One hundred and sixty solved residential burglaries were sampled from a British police force. From these, 80 linked crime pairs (committed by the same serial offender) and 80 unlinked crime pairs (committed by two different serial offenders) were created. Following the methodology used by previous researchers, the behavioural similarity, geographical proximity, and temporal proximity of linked crime pairs were compared with those of unlinked crime pairs. Geographical and temporal proximity possessed a high degree of predictive accuracy in distinguishing linked from unlinked pairs as assessed by logistic regression and receiver operating characteristic analyses. Comparatively, other traditional modus operandi behaviours showed less potential for linkage. Whilst personality psychology literature has suggested we might expect to find a relationship between temporal proximity and behavioural consistency, such a relationship was not observed. Copyright © 2010 John Wiley & Sons, Ltd.
Article
Associating records in a large database that are related but not exact matches has importance in a variety of applications. In law enforcement, this task enables crime analysts to associate incidents possibly resulting from the same individual or group of individuals. In practice, most crime analysts perform this task manually by searching through incident reports looking for similarities. This paper describes automated approaches to data association. We report tests showing that our data association methods significantly reduced the time required by manual methods with accuracy comparable to experienced crime analysts. In comparison to analysis using the structured query language (SQL), our methods were both faster and more accurate.
Conference Paper
Serial criminals are a major threat in the modern society. Associating incidents committed by the same offender is of great importance in studying serial criminals. In this paper, we present a new outlier-based approach to resolve this criminal incident association problem. In this approach, criminal incident data are first modeled into a number of cells, and then a measurement function, called outlier score function, is defined over these cells. Incidents in a cell are determined to be associated with each other when the score is significant enough. We applied our approach to a robbery dataset from Richmond, VA. Results show that this method can effectively solve the criminal incident association problem.
Article
We consider the problem of determining the structure of clustered data, without prior knowledge of the number of clusters or any other information about their composition. Data are represented by a mixture model in which each component corresponds to a different cluster. Models with varying geometric properties are obtained through Gaussian components with different parametrizations and cross-cluster constraints. Noise and outliers can be modelled by adding a Poisson process component. Partitions are determined by the expectation-maximization (EM) algorithm for maximum likelihood, with initial values from agglomerative hierarchical clustering. Models are compared using an approximation to the Bayes factor based on the Bayesian information criterion (BIC); unlike significance tests, this allows comparison of more than two models at the same time, and removes the restriction that the models compared be nested. The problems of determining the number of clusters and the clustering method are solved simultaneously by choosing the best model. Moreover, the EM result provides a measure of uncertainty about the associated classification of each data point. Examples are given, showing that this approach can give performance that is much better than standard procedures, which often fail to identify groups that are either overlapping or of varying sizes and shapes.
Article
The purpose of the present study is to test the case linkage principles of behavioural consistency and behavioural distinctiveness using serial vehicle theft data. Data from 386 solved vehicle thefts committed by 193 offenders were analysed using Jaccard's, regression and Receiver Operating Characteristic analyses to determine whether objectively observable aspects of crime scene behaviour could be used to distinguish crimes committed by the same offender from those committed by different offenders. The findings indicate that spatial behaviour, specifically the distance between theft locations and between dump locations, is a highly consistent and distinctive aspect of vehicle theft behaviour; thus, intercrime and interdump distance represent the most useful aspects of vehicle theft for the purpose of case linkage analysis. The findings have theoretical and practical implications for understanding of criminal behaviour and for the development of decision-support tools to assist police investigation and apprehension of serial vehicle theft offenders.
Using Bayes theorem in behavioural crime linking of serial homicide. Legal and Criminological Psychology
  • B Salo
  • J Sirén
  • J Corander
  • A Zappaì A
  • D Bosco
  • A Mokros
  • P Santtila
Salo, B., Sirén, J., Corander, J.,Zappaì a, A., Bosco, D., Mokros, A. and Santtila, P. (2013) Using Bayes theorem in behavioural crime linking of serial homicide. Legal and Criminological Psychology, 18, 356–370.
State and county quickfacts
  • Us Census
  • Bureau
US Census Bureau (2011) State and county quickfacts. US Census Bureau, Washington DC. (Available from http://quickfacts.census.gov/qfd/states/24/24005.html.)
Linking serious sexual assaults through behaviour. Home Office Research Studies 215
  • D Grubin
  • P Kelly
  • C Brunsdon
Grubin, D., Kelly, P. and Brunsdon, C. (2001) Linking serious sexual assaults through behaviour. Home Office Research Studies 215, London.