About
66
Publications
29,571
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,363
Citations
Citations since 2017
Introduction
Additional affiliations
August 2011 - present
January 2007 - December 2010
Publications
Publications (66)
Machine learning is widely used in information systems design. Yet, training algorithms on imbalanced datasets may severely affect performance on unseen data. For example, in some cases in healthcare, fintech, or cybersecurity contexts, certain subclasses are difficult to learn because they are underrepresented in training data. Our study offers a...
Classifying the sentiments of online reviews of products or services is important in that it provides the analysts with the ability to extract critical information which can be used to improve the corresponding product or service. The objective of this study is to classify the customer reviews (on a five-star and binary scale) that were collected f...
This paper proposes a data-driven framework for multi-target forecasting. We apply the proposed framework to forecast energy load in solar-powered residential houses using meteorological and temporal inputs. We adopt five predictive models of gradient boosting, least angle regression, multi-layer perceptron, random forest, and partial least square...
Objective:
Substance use disorder is a critical public health issue. Discovering the synergies among factors impacting treatment program success can help governments and treatment facilities develop effective policies. In this work, we propose a novel data analytics approach using machine learning models to discover interaction effects that might...
Patients who fail to show up for an appointment are a major challenge to medical providers. Understanding no-shows and predicting them are keys to developing a proactive strategy in healthcare operations. In this study, we propose a data analytics framework to explore the underlying factors of no-shows via various machine learning models to predict...
Patients who miss their appointments (no-shows) reduce revenues and impair the delivery of quality healthcare. Much research has been devoted to identifying “no-show patients”. In this study, we build a Tree Augmented Naïve Bayes (TAN)-based, probabilistic data driven methodology that consists of five steps. After data acquisition and preparation i...
This study is aimed at developing a holistic data analytic approach to measure and improve hospital productivity. It is achieved by proposing a fuzzy logic-based multi-criteria decision-making model so as to enhance business performance. Data Envelopment Analysis is utilized to analyze the productivity and then it is hybridized with the Fuzzy Analy...
This study presents a hybrid framework of Analytic hierarchy process and Intuitionistic Fuzzy Technique for Order of Preference by Similarity to Ideal Solution for the assessment and evaluation of E-commerce web site (EWS) performance. The proposed hybrid model enables decision makers to assess and efficiently use intuitionistic fuzzy numbers. In a...
Business analytics refers to methods and practices that create value through data for individuals, firms, and organizations. This field is currently experiencing a radical shift due to the advent of deep learning: deep neural networks promise improvements in prediction performance as compared to models from traditional machine learning. However, ou...
Mobile banking (MB) has emerged as a strategic differentiator for financial institutions. This study explores the limitations associated with using subjective measures in MB studies that solely rely on survey-based approaches and traditional structural analysis models. We incorporate an objective data analytic approach into measuring usage experien...
The goal of this study is to present a DEA-based fuzzy multi-criteria decision making model for firms in the health care industry in order to enhance their business performance. The study demonstrates a real-life use of the proposed model, mainly designed for hospitals. Data envelopment analysis enhanced with fuzzy analytic hierarchy process are co...
Mobile banking (MB) has emerged as a strategic differentiator for financial institutions. This study explores the limitations associated with using subjective measures in MB studies that solely rely on survey-based approaches and traditional structural analysis models. We incorporate an objective data analytic approach into measuring usage experien...
This study aims to assist marketing managers in identifying locations in which to host peer-to-peer educational events for healthcare professionals (HCPs) throughout the country using data analytics. These events would allow physicians and other HCPs to engage with their peers and learn about the most up-to-date clinical data and research from worl...
Business analytics refers to methods and practices that create value through data for individuals, firms, and organizations. This field is currently experiencing a radical shift due to the advent of deep learning: deep neural networks promise improvements in prediction performance as compared to models from traditional machine learning. However, ou...
The increasing number of new higher education institutions (HEIs) has resulted in a fierce competition for attracting and retaining the best students. In line with these purposes, this study is aimed at devising a student satisfaction index (SSI) model for the HEIs. The SSI model is developed to measure the satisfaction of students in terms of diff...
This study is aimed at determining the future share net inflows and outflows of Exchange Traded Funds (ETFs). The relationship between net flows is closely related to investor perception of the future and past performance of mutual funds. The net flows for Exchange Traded Funds are expected to be less related to overall fund performance, but rather...
No-shows are becoming a major problem in primary care facilities, creating additional costs for the facility while adversely affecting the quality of patient care. Accurately predicting no-shows plays an important role in the overbooking strategy. In this study, a hybrid probabilistic prediction framework based on the elastic net (EN) variable-sele...
In the construction industry, cost estimates are the basis for which projects are awarded to suppliers. A cost estimate is arguably the most important inclusion in a supplier's response to a customer's 'request for quote'. As such, it is essential for construction cost estimates to include features of accuracy, cost effectiveness and profitability...
Feature selection, a critical pre-processing step for data mining, is aimed at determining representative variables/predictors from a large and feature-rich dataset for development of an effective prediction model. The purpose of this paper is to develop a hybrid methodology for feature selection using genetic algorithms to identify such representa...
This paper aims to investigate mobile banking (MB) usage through the theoretical lens of UTAUT model with its four pillars. The research model will be tested via a hybrid neural networks-based structural equation modeling (SEM-NN) to reveal significant factors. Universal structural modeling (USM) will be then utilized to find the hidden paths and n...
College graduation rates have become a primary focus in measuring institutional performance and accountability in higher education. In 2009, President Obama set a goal for the United States to have the highest proportion of college graduates in the world by 2020. With the heightened focus on transparency and accountability in higher education today...
Predicting the survival of heart transplant patients is an important, yet challenging problem since it plays a crucial role in understanding the matching procedure between a donor and a recipient. Data mining models can be used to effectively analyze and extract novel information from large/complex transplantation datasets. The objective of this st...
Purpose
The prediction of graduation rates of college students has become increasingly important to colleges and universities across the USA and the world. Graduation rates, also referred to as completion rates, directly impact university rankings and represent a measurement of institutional performance and student success. In recent years, there h...
Recent research has shown that data mining models can accurately predict the outcome of a heart transplant based on predictors that include patient and donor's health/demographics. These models have not been adopted in practice, however, since they did not: a) consider the interactions between the explanatory variables; b) provide a patient's speci...
The purpose of this study is to develop a hybrid methodology that integrates machine learning algorithms with multi-criteria decision making (MCDM) techniques to effectively conduct multi-attribute inventory analysis. In the proposed methodology, first, ABC analyses using three different MCDM methods (i.e. simple-additive weighting, analytical hier...
Purpose
The purpose of this paper is to provide a model that tests to what extent researchers’ interactions in the early stage of their collaborative network activities affect the number of collaborative outputs (COs) produced (e.g. joint publications, joint grant proposals and joint patents).
Design/methodology/approach
Using self-reports from 10...
Forecasting stock market returns is a challenging task due to the complex nature of the data. This study develops a generic methodology to predict daily stock price movements by deploying and integrating three data analytical prediction models: adaptive neuro-fuzzy inference systems, artificial neural networks, and support vector machines. The prop...
This paper presents a fuzzy lung allocation system (FLAS) in order to determine which potential recipients would receive a lung for transplantation when it becomes available in the USA. The developed system deals with the vagueness and fuzziness of the decision making of the medical experts in order to achieve accurate lung allocation processes in...
The primary aim of this study is to determine critical factors of knowledge management (KM) and to measure their effect on organisational performance. The design of the study is based on a survey composed of questions related to the KM processes. Following refinement and retesting the initial questionnaire development, the final questionnaire was s...
The problem of effectively preprocessing a dataset containing a large number of performance metrics and an even larger number of records is crucial when utilizing an ANN. As such, this study proposes deploying DEA to preprocess the data to remove outliers and hence, preserve monotonicity as well as to reduce the size of the dataset used to train th...
Third-party logistics (3PL) service provider selection for a strategic alliance is not an easy decision, and is constantly associated with uncertainty and complexity. For this reason, in this study, a hybrid fuzzy multi-criteria decision-making methodology is proposed to provide a systematic decision support tool for 3PL provider evaluation, especi...
This research investigates the application of Bayesian Networks to predict causal relationships in a dataset that captures several demographic and academic features of a group of students from a four-year public university. This educational dataset is characterized by both quantitative and qualitative variables, some of which exhibit a strong pair-...
The purpose of this paper is to develop an early warning system to predict currency crises. In this study, a data set covering the period of January 1992–December 2011 of Turkish economy is used, and an early warning system is developed with artificial neural networks (ANN), decision trees, and logistic regression models. Financial Pressure Index (...
Most business students in universities across the United States find the quantitatively oriented courses challenging to comprehend the course material to a degree necessary to develop capability and confidence level to solve business problems. A determination of critical factors that influence performance in such courses is critical to designing cl...
This mini-track has five papers that are about developing systems for decision support by means of data, text, or web mining. These five papers focus on a wide range of application areas from healthcare to social media, reinforcing the fact that data, text, and web mining are effective and recently popularized tools to develop decision support syst...
This study is aimed at determining the future share net inflows and outflows by using the characteristics of Exchange Traded Funds (ETF) as variables in a data mining based analytic methodology. The relationship between net flows is closely related to investor perception of the future and past performance of mutual funds. In order to explore the re...
The research presented in this paper proposes a new machine learning-based evaluation method for assessing the usability of eLearning systems. Three machine learning methods (support vector machines, neural networks and decision trees) along with multiple linear regression are used to develop prediction models in order to discover the underlying re...
Purpose
– Previous researches have proven that customer satisfaction and loyalty are affected by complicated relationships and are challenging to European customer satisfaction index (ECSI) model. Existing approaches mostly limit their hypotheses to linear relationships, which hinder much information that would lead to better modeling and understan...
Introduction to Predictive Analytics and Big Data Minitrack.
Predicting the performance of planned organ transplantation has proved to be a critical problem to solve. The purpose of this study is to present a data mining-based model for variable filtering and selection in order to predict the performance of thoracic transplantation via the graft survivability after the transplant. To this end, 10-fold cross-...
Special Issue Editors: Vincent Charles, Rolf Fare and Joe Zhu
Foreword: Business Performance Management is a term that became widely used in the 1970s. The term represents a set of activities that assist the management of any organization to manage its resources and achieve its goals in an effective and efficient manner. Basically, it is a popular...
Demand for high-quality, affordable healthcare services increasing with the aging population in the US. In order to cope with this situation, decision makers in healthcare (managerial, administrative and/or clinical) need to be increasingly more effective and efficient at what they do. Along with expertise, information and knowledge are the other k...
Lung transplantation has a vital role among all organ transplant procedures since it is the only accepted treatment for the end-stage pulmonary failure. There have been several research attempts to model the performance of lung transplants. Yet, these early studies either lack model predictive capability by relying on strong statistical assumptions...
In this study, a decision support system (DSS) for usability assessment and design of web-based information systems (WIS) is proposed. It employs three machine learning methods (support vector machines, neural networks, and decision trees) and a statistical technique (multiple linear regression) to reveal the underlying relationships between the ov...
This article is aimed at applying Taguchi method in Kansei engineering and explores a way to integrate it into an industrial product design stage. Emotional customer needs are derived using Kansei image word pairs. The Taguchi-based approach is validated by a case study with mobile phones. Experimental work in implementing the proposed approach was...
This paper proposes a new usability evaluation checklist, UseLearn, and a related method for eLearning systems. UseLearn is a comprehensive checklist which incorporates both quality and usability evaluation perspectives in eLearning systems. Structural equation modeling is deployed to validate the UseLearn checklist quantitatively. The experimental...
Chemical mechanical planarization (CMP) process has been widely used in the semiconductor manufacturing industry for realizing highly finished (Ra ~ 1 nm) and planar surfaces (WIWNU ~ 1%, thickness standard deviation (SD) ~ 3 nm) of in-process wafer polishing. The CMP process is rather complex with nonlinear and non-Gaussian process dynamics, which...
This study is aimed at optimising the RFID network design in the healthcare service sector for tracking medical assets. Two different optimisation models corresponding to two possible scenarios in RFID network design are developed based on the enhancement of location set covering problem (LSCP) and maximal covering location problem (MCLP). They are...
The purpose of this research is to provide decision makers with a methodology to optimize the design of a medical-asset tracking system constrained by a limited number of RFID readers. Using an enhanced formulation of the maximal covering location problem along with a new criticality index analysis metric (derived from the severity, frequency and d...
Objective:
The prediction of survival time after organ transplantations and prognosis analysis of different risk groups of transplant patients are not only clinically important but also technically challenging. The current studies, which are mostly linear modeling-based statistical analyses, have focused on small sets of disparate predictive facto...
A methodology for usability assessment and design of web-based information systems (UWIS) is proposed. It combines web-based service quality and usability dimensions of information systems. Checklist items with the highest and the lowest contribution to the usability performance of a web-based information system can be specified by UWIS. A case stu...
Modeling of variation propagation in multistation assembly processes is crucial in predicting product dimensional quality and general performance of manufacturing systems. Based on the state space modeling, this paper develops a variation propagation model, which can be applied for analysis of various tolerances such as size tolerance, bonus tolera...
Background:
Predicting the survival of heart-lung transplant patients has the potential to play a critical role in understanding and improving the matching procedure between the recipient and graft. Although voluminous data related to the transplantation procedures is being collected and stored, only a small subset of the predictive factors has be...
This paper aims to determine the optimum number of RFID readers and their placement for asset tracking. To achieve this goal, an optimization model based on location set covering problem (LSCP) is established. It is implemented in a healthcare facility and the required number of readers for full coverage was determined under certain constraints. Th...
This paper is aimed at determining of the effect of subjective measures of web service usability on its objective measures. Using these results by appropriate design of web system its usability can be improved. A checklist combining the dimensions of web service usability and web service quality is proposed. For determining the subjective measures...
Projects
Projects (3)
Please visit and consider submitting to the Business Analytics Track of DSI: https://decisionsciences.org/annual-meetings/national-dsi/tracks-and-track-chairs/
Modeling, synthesis, and diagnosis for large and complex manufacturing systems, with applications in automobile assembly systems.
Data Mining & Decision Analytics (DMDA) Workshop
November 12, 2016 Nashville, TN
The Data Mining, Analytics, Artificial Intelligence, Quality, Statistics & Reliability, Multi-Criteria Decision Making Sections, and Health Applications Society of INFORMS is organizing the 2016 INFORMS Workshop on Data Mining and Decision Analytics on November 12, 2016 in Nashville, TN in conjunction with the 2016 INFORMS Annual Conference.
Timeline:
June 30: maximum of 15-page papers due
August 5: First round of review decisions sent out
September 5: Revised papers due
October 5: Second round of review decisions sent out
November 12: Workshop
Registration Fees
All participants should pay the full amount of the regular Informs Conference Registration fee and additionally below listed fee to participate at this workshop. These below listed fees include full-day meal courses (breakfast, lunch, and dinner) for the day of November 12. Only the registered participants (both to the Informs Conference and to the DMDA Workshop itself) would be eligible to present, participate, and audit the event.
Students: $75.00 per student
Non-Students: $150.00 per non-student
Sponsors of the DMDA Workshop
TBA soon…
Highlights of the DMDA Workshop
• Best Paper Presentation Contest
Authors of all papers which are accepted after a rigorous two-round review process AND after an in-person presentation at the workshop would be eligible for this contest. The contest is focused on coherence between the content of the paper as well as the presentation. It will be judged by a panel of DMDA Workshop co-chairs and session chairs on any topic related to data mining & decision analytics. In addition to a name-engraved plaque, following monetary awards would be presented to the winners:
1st place: $300; 2nd place: $200; 3rd place: $100
• Publication opportunity at the special issue:
Participants of this workshop are encouraged to submit their extended manuscripts to the special issue of Data Mining & Decision Analytics at the Decision Sciences journal. For more information, contact the special issue guest editor Dr. Asil Oztekin at Asil_Oztekin@uml.edu
• Editors’ Panel: How to publish in top-tier journals?
Top-tier premier outlets of the leading journals in the field of data mining and decision analytics would be represented by their respective editors. After a short presentation of the editors (5 minutes each), there will be a Q&A session, in which the audience would have chance to ask questions to the editors. The following list of editors (and the corresponding journals they would represent in alphabetical order) will be participating at this panel:
Annals of Operations Research—Dr. Endre Boros
Decision Sciences—Dr. Cheri Speier-Pero
Decision Support Systems—Dr. James Marsden
European Journal of Operational Research—Dr. Roman Slowinski
Information Systems Frontiers—Dr. Ram Ramesh
INFORMS Journal on Computing—Dr. David Woodruff
Journal of the Association of Information Science & Technology—Dr. Javed Mostafa
Journal of Multi-Criteria Decision Analysis—Dr. Gilberto Montibeller
Manufacturing & Service Operations Management—Dr. Brian Tomlin
Omega: the International Journal of Management Science—Dr. Ben Lev
Production & Operations Management—Dr. Subodha Kumar
• Keynote Speakers of the DMDA Workshop:
Dr. Amit Basu is the Carr P. Collins Chair of Management Information Sciences at the Edwin L. Cox School of Business at Southern Methodist University where he serves as the Chairman of the Information Technology and Operations Management department. His research and teaching interests are in the areas of decision support systems, knowledge and data base systems, and ecommerce. He has published papers on these topics in a variety of top-tier outlets such as Management Science, Information Systems Research, Decision Support Systems, European Journal of Operational Research, Journal of Management Information Systems, and Omega. He has served on the editorial boards of several leading academic journals – he has been the Area Editor for INFORMS Journal on Computing, and Associate Editor for Management Science, Information Systems Research, the Information Technology and Management Journal, and an Editorial Board Member for the POMS Journal. From 2012-2013, he served as the President of the INFORMS Information Systems Society.
Dr. David L. Olson is the James & H.K. Stuart Professor in MIS and Chancellor’s Professor at the University of Nebraska. He has published research in over 150 refereed journal articles, primarily on the topic of data mining, multi-objective decision making, and information technology. Additionally, he has co-authored the books Advanced Data Mining Techniques, Introduction to Business Data Mining, Enterprise Risk Management, Enterprise Information Systems, Enterprise Risk Management Models, and Financial Enterprise Risk Management. He has served as associate editor of Decision Support Systems, Decision Sciences, and Service Business, and co-editor in chief of International Journal of Services Sciences. He was a Lowry Mays endowed Professor at Texas A&M University from 1999 to 2001. He was named the Raymond E. Miles Distinguished Scholar award for 2002, and was a James C. and Rhonda Seacrest Fellow from 2005 to 2006. He is a Fellow of the Decision Sciences Institute.
Dr. Nick Street received a Ph.D. in Computer Sciences from the University of Wisconsin-Madison in 1994. He is currently professor, departmental executive officer, and Henry B. Tippie Research Professor in the Management Sciences Department at the University of Iowa, with joint appointments in the Computer Science Department, the College of Nursing, and the Interdisciplinary Graduate Program in Informatics. He is also the director of the interdisciplinary graduate program in Health Informatics. His research interests are in algorithmic approaches to machine learning and data mining, particularly the use of mathematical optimization in inductive learning techniques. His recent work has focused on ensemble construction methods, knowledge transfer, correlation analysis, statistical relational learning, personalized medical decision making, and social network analysis. He has published over 110 journal, conference and workshop papers, and has received an NSF CAREER award and an NIH INRSA postdoctoral fellowship. He is a member of INFORMS, IEEE, ACM, AAAI, and AMIA.
Dr. Olivia Sheng is Presidential Professor and Emma Eccles Jones Presidential Chair of Information Systems at the David Eccles School of Business, and an Adjunct Professor at School of Computing, University of Utah. She also directs the Global Knowledge Management Center to seek research and education extension of business intelligence and analytics, and organizes one of the first academic conferences on business intelligence annually. Her research focuses on web, text, and data mining as well as optimization techniques for clickstream analysis, social network analysis, search marketing, crowd-based predictive analytics, behavior targeting, bio-medical, digital government, telemedicine and telework applications. Her research has received funding from U.S. Food and Drug Administration, National Science Foundation, Overstock, Yahoo!, U.S. Army, IBM Tivoli, Toshiba Corp., Sun Microsystems, SAP University Alliance, and Wasatch Advisors. Currently, she engages companies in Utah such as Backcountry and Intermountain Healthcare Company to collaborate on research and capstone projects related to text mining and data mining.
Papers should follow the belowlisted guidelines:
• Maximum of 15 pages (including all-abstract, references, tables, and figures)
• 11-point font with one-inch margins on four sides
• Double-spaced
Making Your Presentation
1. Go to the registration area of the Informs conference between 7:00am -5:00pm and pick up your name badge and other registration materials.
2. Arrive at your session at least 15 minutes early for A/V set-up and to check in with the session chair.
3. Limit your presentation to key issues with a brief summary.
4. Time your presentation to fit within your designated time span, leaving time for audience questions. Time per speaker is determined by the number of papers in the session, with equal time given to each paper.
5. Bring copies of your paper or other handouts to distribute to the audience.
Courtesy to Fellow Speakers
Attendees are asked to be respectful of their colleagues by turning off cell phones and mobile devices before the presentations begin. In addition, please note that use of cameras and all recording devices is prohibited during sessions unless you have received prior permission from the speaker and the session chair.
Session Chair Guidelines
The role of the Chair is to coordinate the smooth running of the session.
The Chair:
1. Begins and ends the session on time. Each session lasts 90 minutes, with the time per presentation determined by the number of papers in the session. Equal time should be given to each paper.
2. Introduces each presentation (just the title of the paper and the name of the presenting author).
3. Ensures that presentations are made in the order shown in the program. This allows for “session jumping.” If a speaker cancels or does not attend, the original time schedule should be adhered to rather than sliding every talk forward.
4. Completes the session attendance forms (forms will be in the room).
5. Reminds the audience to (a) turn off all mobile devices and (b) that photography is not allowed without the prior permission of the speaker.
Late Cancellations & No-Shows
Please don’t be a “no-show.” While we understand that last-minute emergencies may prevent speakers from attending, we urge you to inform us so we can alert attendees. Speakers who fail to notify us that they are not attending are being unfair to their colleagues and the Organizing Committee. In an effort to improve the quality of the meeting, we maintain records of individuals who are late cancellations and “no-shows.” These people may be required to register in advance for future meetings in order for their papers to be scheduled. Send cancellation in writing a couple days prior the workshop to the managing chair, Dr. Asil Oztekin, with the reason for canceling.
If a speaker is a “no-show,” the original time schedule should be adhered to rather than sliding every talk forward. This allows for effective session jumping.
For inquiries, please contact Workshop co-Chairs:
Asil Oztekin (University of Massachusetts Lowell, Department of Operations & Information Systems): Asil_Oztekin@uml.edu (Managing Chair)
Cem Iyigun (Middle East Technical University, Department of Industrial Engineering): Iyigun@metu.edu.tr
Ramin Moghaddess (University of Miami, Department of Industrial Engineering): Ramin@miami.edu
Management Committee:
Tom Au (AT&T Labs)
Victoria Chen (University of Texas at Arlington)
Kwok-Leung Tsui (Georgia Institute of Technology)
Cynthia Rudin (MIT)
George Runger (Arizona State University)