No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Artificial Intelligence in Online Stores' Processes
Abstract
The global e-commerce market has been growing rapidly, even more so due to the COVID-19 pandemic which caused a number of stationery stores to close down. At the same time, Artificial Intelligence (AI) has also gained prominence. In this article, we review and describe the practical applications of AI which is helping e-commerce businesses. In particular, we have concentrated on AI in some key areas of e-commerces such as online marketing, operations in fulfillment centers, barcode identification , and autonomous delivery methods. The findings and conclusions in this article would be useful for researchers as well as businesses to get an overview of the landscape of AI applications in e-commerces.
ResearchGate has not been able to resolve any citations for this publication.
New internet-based technologies have changed the way business enterprises handle marketing, discovery, transaction processing, and product and customer service processes. One of the significant technologies is artificial intelligence (AI), which has partially or completely substituted humans for the performance of tasks. In a technology-driven industry such as e-commerce, the applications of AI are immense. To explicate the impact of AI as a technological phenomenon on the companies engaged in e-commerce, this chapter will detail the role of AI under e-commerce business processes like market research, market stimulation, terms negotiation, order selection and priority, order receipt, order billing/payment management, order scheduling/fulfillment delivery, and customer service and support.
Artificial intelligence (AI) will substantially impact retailing. Building on past research and from interviews with senior managers, we examine how senior retailing managers should think about adopting AI, involving factors such as the extent to which an AI application is customer-facing, the amount of value creation, whether the AI application is online, and extent of ethics concerns. In addition, we highlight that the near-term impact of AI on retailing may not be as pronounced as the popular press might suggest, and also that AI is likely to be more effective if it focuses on augmenting (rather than replacing) managers’ judgments. Finally, while press coverage typically involves customer-facing AI applications, we highlight that a lot of value can be obtained by adopting non-customer-facing applications. Overall, we remain very optimistic as regards the impact of AI on retailing. Finally, we lay out a research agenda and also outline implications for practice.
Autonomous mobile robots (AMR) are currently being introduced in many intralogistics operations, like manufacturing, warehousing, cross-docks, terminals, and hospitals. Their advanced hardware and control software allow autonomous operations in dynamic environments. Compared to an automated guided vehicle (AGV) system in which a central unit takes control of scheduling, routing, and dispatching decisions for all AGVs, AMRs can communicate and negotiate independently with other resources like machines and systems and thus decentralize the decision-making process. Decentralized decision-making allows the system to react dynamically to changes in the system state and environment. These developments have influenced the traditional methods and decision-making processes for planning and control. This study identifies and classifies research related to the planning and control of AMRs in intralogistics. We provide an extended literature review that highlights how AMR technological advances affect planning and control decisions. We contribute to the literature by introducing an AMR planning and control framework to guide managers in the decision-making process, thereby supporting them to achieve optimal performance. Finally, we propose an agenda for future research within this field.
Despite heightened interest, integrating artificial intelligence (AI) into businesses remains challenging. Recent surveys show that up to 85 % of AI initiatives ultimately fail to deliver on their promises. Studies on successful AI applications that could provide invaluable lessons for organizations embarking on their AI journey are still lacking. Therefore, this study aims to understand how AI technology, people, and processes should be managed to successfully create value. Building on the resource orchestration perspective, this study analyzes the successful applications of AI at Alibaba's e-commerce fulfillment center. The findings indicate that the key AI resources include data, AI algorithms, and robots. These resources must be orchestrated (e.g., coordinated, leveraged, deployed) to work with other related resources, such as warehouse facilities and existing information systems, to generate strong AI capabilities. The key AI capabilities generated include forecasting, planning, and learning. More importantly, AI capabilities are not independent – they interact and coevolve with human capabilities to create business value in terms of efficiency (e.g., space optimization, labor productivity) and effectiveness (e.g., error reduction). The implications of understanding these social informatics of AI for research and practice are discussed.
Time is an essential resource for everyone wants to save in their life. The development of technology inventions made this possible up to certain limit. Due to life style changes people are purchasing most of their needs on a single shop called super market. As the purchasing item numbers are huge, it consumes lot of time for billing process. The existing billing systems made with bar code reading were able to read the details of certain manufacturing items only. The vegetables and fruits are not coming with a bar code most of the time. Sometimes the seller has to weight the items for fixing barcode before the billing process or the biller has to type the item name manually for billing process. This makes the work double and consumes lot of time. The proposed artificial intelligence based image classification system identifies the vegetables and fruits by seeing through a camera for fast billing process. The proposed system is validated with its accuracy over the existing classifiers Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF) and Discriminant Analysis (DA).
In the future, artificial intelligence (AI) is likely to substantially change both marketing strategies and customer behaviors. Building from not only extant research but also extensive interactions with practice, the authors propose a multidimensional framework for understanding the impact of AI involving intelligence levels, task types, and whether AI is embedded in a robot. Prior research typically addresses a subset of these dimensions; this paper integrates all three into a single framework. Next, the authors propose a research agenda that addresses not only how marketing strategies and customer behaviors will change in the future, but also highlights important policy questions relating to privacy, bias and ethics. Finally, the authors suggest AI will be more effective if it augments (rather than replaces) human managers.
Purpose
The purpose of this paper is to investigate how warehouse management, understood as a cluster of planning and control decisions and procedures, is organized and driven by task complexity (TC) and market dynamics (MD).
Design/methodology/approach
A multi‐variable conceptual model is developed based on the literature and tested among 215 warehouses using a survey.
Findings
The results suggest that TC and MD are the main drivers of warehouse management, measured by planning extensiveness (PE), decision rules complexity, and control sophistication. Differences between production and distribution warehouses are found with respect to the relationship between assortment changes and PE. Furthermore, TC appears to be a main driver of the specificity of the warehouse management (information) system (WMS).
Research limitations/implications
This paper is based on 215 warehouses in The Netherlands and Flanders (Belgium); future research may test the model on a different sample. More research should be conducted to further validate the measures of the core dimensions of warehouse management.
Practical implications
Different levels of TC and MD characterize warehouses. Such a characterization is a first step in determining generic warehouse functionalities and helping managers to decide on the best software for their warehouse operations.
Originality/value
The paper defines the core dimensions of warehouse management, makes them measurable, tests them and assesses how these drivers impact specificity of WMS. The paper shows that PE in production warehouses is driven by different variables than in distribution centers.
Barcode reading mobile applications that identify products from pictures taken using mobile devices are widely used by customers to perform online price comparisons or to access reviews written by others. Most of the currently available barcode reading approaches focus on decoding degraded barcodes and treat the underlying barcode detection task as a side
problem that can be addressed using appropriate object detection methods. However, the majority of modern mobile devices do not meet the minimum working requirements of complex general purpose object detection algorithms and most of the efficient specifically designed barcode detection algorithms require user interaction to work properly. In this paper, we present a novel method for barcode detection in camera captured images based
on a supervised machine learning algorithm that identifies onedimensional barcodes in the two-dimensional Hough Transform space. Our model is angle invariant, requires no user interaction and can be executed on a modern mobile device. It achieves excellent results for two standard one-dimensional barcode datasets: WWU Muenster Barcode Database and ArTe-Lab 1D Medium Barcode Dataset. Moreover, we prove that it is possible to enhance the overall performance of a state-of-the-art barcode reading algorithm by combining it with our detection method.
Barcode reading mobile applications that identify products from pictures taken using mobile devices are widely used by customers to perform online price comparisons or to access reviews written by others. Most of the currently available barcode reading approaches focus on decoding degraded barcodes and treat the underlying barcode detection task as a side problem that can be addressed using appropriate object detection methods. However, the majority of modern mobile devices do not meet the minimum working requirements of complex general purpose object detection algorithms and most of the efficient specifically designed barcode detection algorithms require user interaction to work properly. In this paper, we present a novel method for barcode detection in camera captured images based on a supervised machine learning algorithm that identifies one-dimensional barcodes in the two-dimensional Hough Transform space. Our model is angle invariant, requires no user interaction and can be executed on a modern mobile device. It achieves excellent results for two standard one-dimensional barcode datasets: WWU Muenster Barcode Database and ArTe-Lab 1D Medium Barcode Dataset. Moreover, we prove that it is possible to enhance the overall performance of a state-of-the-art barcode reading algorithm by combining it with our detection method.
Social networking site (SNS) driven e-commerce, the latest social commerce (s-commerce) phenomenon, gains prominence with the introduction of the call-to-action feature. The call-to-action feature on any sponsored post or advertisement on SNS redirects the user to a linked e-commerce website that offers the product. Information cues available on the SNS are expected to influence user decision making on the linked e-commerce site. Set in the context of Facebook driven e-commerce, this study explores how likes on Facebook influence user's purchase and recommendation decisions on a linked e-commerce website. Using controlled experiments we find that a higher volume of likes on Facebook leads to a higher likelihood of purchasing and recommending a product on the linked e-commerce site. This effect is found to be mediated by the user's initial product attitude formed on Facebook. An additional analysis examining the strength of the influence reveals that the mere presence of likes is not sufficient to impact the user's decision making. In fact, a low volume of likes elicits user behavior similar to absence of likes. The influence is effective only if the number of likes is substantially high. The findings of the study add to the s-commerce literature by establishing the inter-site influence of Facebook likes on user's purchase and post-purchase decisions and providing empirical evidence of the efficacy of SNS-driven e-commerce.
As far back as the industrial revolution, significant development in technical innovation has succeeded in transforming numerous manual tasks and processes that had been in existence for decades where humans had reached the limits of physical capacity. Artificial Intelligence (AI) offers this same transformative potential for the augmentation and potential replacement of human tasks and activities within a wide range of industrial, intellectual and social applications. The pace of change for this new AI technological age is staggering, with new breakthroughs in algorithmic machine learning and autonomous decision-making, engendering new opportunities for continued innovation. The impact of AI could be significant, with industries ranging from: finance, healthcare, manufacturing, retail, supply chain, logistics and utilities, all potentially disrupted by the onset of AI technologies. The study brings together the collective insight from a number of leading expert contributors to highlight the significant opportunities, realistic assessment of impact, challenges and potential research agenda posed by the rapid emergence of AI within a number of domains: business and management, government, public sector, and science and technology. This research offers significant and timely insight to AI technology and its impact on the future of industry and society in general, whilst recognising the societal and industrial influence on pace and direction of AI development.
Robotic handling systems are increasingly applied in distribution centers. They require little space, provide flexibility in managing varying demand requirements, and are able to work 24/7. This makes them particularly fit for e-commerce operations. This paper reviews new categories of automated and robotic handling systems, such as shuttle-based storage and retrieval systems, shuttle-based compact storage systems, and robotic mobile fulfillment systems. For each system, we categorize the literature in three groups: system analysis, design optimization, and operations planning and control. Our focus is to identify the research issue and operations research modeling methodology adopted to analyze the problem. We find that many new robotic systems and applications have hardly been studied in academic literature, despite their increasing use in practice. Because of unique system features (such as autonomous control, flexible layout, networked and dynamic operation), new models and methods are needed to address the design and operational control challenges for such systems, in particular, for the integration of subsystems. Integrated robotic warehouse systems will form the next category of warehouses. All vital warehouse design, planning, and control logic, such as methods to design layout, storage and order-picking system selection, storage slotting, order batching, picker routing, and picker to order assignment, will have to be revisited for new robotized warehouses.
E-commerce retailers face the challenge to assemble large numbers of time-critical picking orders each consisting of just a few order lines with low order quantities. Traditional picker-to-parts warehouses are often ill-suited for these prerequisites, so that automated warehousing systems (e.g., automated picking workstations, robots, and AGV-assisted order picking systems) are applied and organizational adaptions (e.g., mixed-shelves storage, dynamic order processing, and batching, zoning and sorting systems) are made in this branch of industry. This paper is dedicated to these warehousing systems especially suited for e-commerce retailers. We discuss suited systems, survey the relevant literature, and define future research needs.
Block geometry is commonly the most important feature determining the behaviour of a rock mass and directly controls the structural instability in underground openings or surface cuttings. Various methods are used to estimate block geometry and to perform a block survey, and these are standardly divided into empirical-based methods (e.g. spot mapping, linear mapping, areal mapping) and computer-based methods (e.g. laser scanning, image processing, digital image mapping). Empirical approaches are associated with effective features as well as with a number of errors; however, the latter can be covered by artificial intelligence (AI) techniques. The combination of image processing and areal mapping have led to geometric block estimation in two-dimensional (2D) and three-dimensional (3D) spaces; these approaches can be widely used in stability analysis, dimension stone extraction, excavations, open pit mining design and the delineation of blasting patterns for dimension stone extraction. Therefore, the application of an approach that allows both the modelling and production of rock blocks based on their actual status with qualified accuracy and speed are both worthwhile and necessary. In this study, to estimate the shape and block dimension utilized, we used the algorithm based on the AI image processing technique for rock mass structural detection and for rock block definition in 2D and 3D space obtained with the Mathematica software package. The algorithm, by categorizing the discontinuities in two groups (opened and closed), which represents the main and the secondary discontinuities, can identify the emplacement and shape of rock blocks.
Define EC order fulfillment and describe the EC order fulfillment process.
Amazon is well-known for personalization and recommendations, which help customers discover items they might otherwise not have found. In this update to their original paper, the authors discuss some of the changes as Amazon has grown.
Content-based medical image retrieval can support diagnostic decisions by clinical experts. Examining similar images may provide clues to the expert to remove uncertainties in his/her final diagnosis. Beyond conventional feature descriptors, binary features in different ways have been recently proposed to encode the image content. A recent proposal is “Radon barcodes” that employ binarized Radon projections to tag/annotate medical images with content-based binary vectors, called barcodes. In this paper, MinMax Radon barcodes are introduced which are superior to “local thresholding” scheme suggested in the literature. Using IRMA dataset with 14,410 x-ray images from 193 different classes, the advantage of using MinMax Radon barcodes over thresholded Radon barcodes are demonstrated. The retrieval error for direct search drops by more than 15%. As well, SURF, as a well-established non-binary approach, and BRISK, as a recent binary method are examined to compare their results with MinMax Radon barcodes when retrieving images from IRMA dataset. The results demonstrate that MinMax Radon barcodes are faster and more accurate when applied on IRMA images.
The architecture of an artificial neural network defines how its several neurons are arranged, or placed, in relation to each other. These arrangements are structured essentially by directing the synaptic connections of the neurons.
Traditional laser barcode reader is affected by reading distance and barcode deformation. A fusion of decision tree and AdaBoost algorithm based barcode image recognition method is proposed in this study. Combining barcode image characteristics, a 5-dimensional feature extraction method is applied to define the barcode image. The result shows that this method can accurately identify barcode form in any angle and any distance within line sight, and also can effectively identify dirty barcode. This method greatly enhances the barcode reading, and can be applied in goods checking and sorting in logistics system.
this paper,they also use the level set decomposition to filter the level lines of an image, thenreconstruct it thanks to monotonicity. The decomposition was later made easier byMonasse and Guichard's algorithm [128, 129], that we used for our experiments.Uniform consistency for the Lipschitz case (Sect. 6.4.1 and Lem. 6.20) is obtainedthanks to the localizability of the affine erosion (Moisan [125]). Localizability wasintroduced by Guichard and Morel [81]. The convergence Theorem 6.27 is...
In this paper, a bar-code recognition system using neural networks is proposed. It is well known that in many stores laser bar-code readers are used at check-out counters. However, there is a major constraint when this tool is used. That is, unlike traditional camera-based picturing, the distance between the laser reader (sensor) and the target object is close to zero when the reader is applied. This may result in inconvenience in store automation because the human operator has to manipulate either the sensor or the objects, or both. For the purpose of in-store automation, the human operator needs to be removed from the process, i.e. a robot with visual capability is required to play an important role in such a system. This paper proposes a camera-based bar-code recognition system using backpropagation neural networks. The ultimate goal of this approach is to use a camera instead of a laser reader so that in-store automation can be achieved. There are a number of steps involved in the proposed system. The first step the system has to perform is to locate the position and orientation of the bar code in the acquired image. Secondly, the proposed system has to segment the bar code. Finally, a trained backpropagation neural network is used to perform the bar-code recognition task. Experiments have been conducted to corroborate the efficiency of the proposed method.
The purpose of this paper is to carry out an exploratory investigation into the emerging interactions between young consumers and consumer products/services on social networks. In particular, we examine the extent to which a small exploratory sample of participants are willing to incorporate social shopping behaviour, namely, product/service recommendations and retail purchase activities. We draw upon a qualitative study of four focus groups carried out with students at two UK-based universities. The results lead us to suggest specific avenues of enquiry that could be pursued in future larger scale work in this new area of consumer behaviour research. We note that for our participants, a ‘nudge’ in the form of recommendations from friends appears to be influential in changing online shopping behaviour and that a hierarchy of trust ordinal scale in recommenders/reviewers ranging from ‘real’ friends at the top down to reviews on retailers’ websites may be positively associated with intention to purchase. Copyright © 2011 John Wiley & Sons, Ltd.
Flexible and timely warehousing activities provide a strong foundation for logistic systems. However, increasing B2C e-commerce
with a variety of small internet orders may have a tremendous impact on warehousing. Automated storage/retrieval systems (AS/RSs)
are a valid alternative for warehousing. Typical AS/RSs design and control problems in a static environment and cannot effectively
manage parcel, small, and irregular items. This study proposes a new AS/RS that is more efficient and flexible for handling
B2C e-commerce logistics. An auto-access multilevel conveying device (IMCD) with three-dimensional movement is integrated
into the AS/RS. The ant colony system algorithm locates near-optimal routes for the IMCD. Typical travel distance/time measures
evaluate the performance of an S/R device running on a warehouse floor. However, the performance index in this study looks
at the IMCD’s travel time with three-dimensional movement in completing a batch order. To validate the new AS/RS, two simulation
experiments were conducted to examine the effects of three-dimensional velocity and rack shape. Finally, this study compares
a typical S/R system with the new AS/RS and makes recommendations for practical applications and further research.
KeywordsE-commerce logistic-Automated storage and retrieval system-Material handling device-Ant algorithm
Barcodes have been widely used in many industrial products for automatic identification in data collection and inventory control purposes. It is well known that in many stores laser bar-code readers are used at check-out counters. However, there is a major constraint when this tool is used. That is, unlike traditional camera-based picturing, the distance between the laser reader (sensor) and the target object is close to zero when the reader is applied. This may result in inconvenience in inspection automation because the human operator has to manipulate either the sensor or the objects. For the purpose of in-store or inspection automation, the human operator needs to be removed from the process, i.e. a robot with visual capability is required to play an important role in such a system. Moreover, an automated system is required to find, locate and decode barcodes on various document images even with low resolution compared with laser barcode readers (about 15,000 dots per inch) and can handle damaged bar codes. This paper proposes a smart barcode detection and recognition system (SBDR) based on fast hierarchical Hough transform (HHT). The back-propagation neural network (BPNN) is selected as a powerful tool to perform the recognition process. The paper presents an effective method to utilize the specific graphic features of barcodes for positioning and recognition purposes even in case of distorted barcodes. The first step the system has to perform is to locate the position and orientation of the barcode in the required material document image. Secondly, the proposed system has to segment the barcode. Finally, a trained back-propagation neural network is used to perform the barcode recognition task. Experiments have been conducted to corroborate the efficiency of the proposed method.
A robust and fast skew detection algorithm based on hierarchical Hough transform is proposed. It is capable of detecting the skew angle for various document images, including technical articles, postal labels, handwritten text, forms, drawings and bar codes. The algorithm is robust even when black margins introduced by photocopying are present in the image and when the document is scanned at a low resolution of 50 dpi. The algorithm consists of two steps. In the first step we quickly extract the centroids of connected components using a graph data structure. Then, a hierarchical Hough transform (at two different angular resolutions) is applied to the selected centroids. The skew angle corresponds to the location of the highest peak in the Hough space. The performance of the algorithm is shown on a number of document images collected from various application domains. The algorithm is not very sensitive to algorithmic parameters. For an A4 size document image scanned at 50 dpi (typically 413 × 575 pixels), our algorithm is able to detect the skew angle with an accuracy of 0.1° in 0.4s of CPU time on a SunSparc 20 workstation.
Human eyes are most sophisticated organ, with perfect and interrelated subsystems such as retina, pupil, iris, cornea, lens and optic nerve. The eye disorder such as cataract is a major health problem in the old age. Cataract is formed by clouding of lens, which is painless and developed slowly over a long period. Cataract will slowly diminish the vision leading to the blindness. At an average age of 65, it is most common and one third of the people of this age in world have cataract in one or both the eyes. A system for detection of the cataract and to test for the efficacy of the post-cataract surgery using optical images is proposed using artificial intelligence techniques. Images processing and Fuzzy K-means clustering algorithm is applied on the raw optical images to detect the features specific to three classes to be classified. Then the backpropagation algorithm (BPA) was used for the classification. In this work, we have used 140 optical image belonging to the three classes. The ANN classifier showed an average rate of 93.3% in detecting normal, cataract and post cataract optical images. The system proposed exhibited 98% sensitivity and 100% specificity, which indicates that the results are clinically significant. This system can also be used to test the efficacy of the cataract operation by testing the post-cataract surgery optical images.
Modeling the global economic impact of AI. McKinsey Global Institute
- J Bughin
- J Seong
- J Manyika
- M Chui
- R Joshi
Bughin, J., Seong, J., Manyika, J., Chui, M., Joshi, R.: Modeling the global
economic impact of AI. McKinsey Global Institute. https://www.mckinsey.com/
featured-insights/artificial-intelligence/notes-from-the-ai-frontier-modeling-theimpact-of-ai-on-the-world-economy. Accessed 19 Sept 2021
A study of artificial intelligence and e-commerce ecosystem-a customer’s perspective
- R Singh
Singh, R.: A study of artificial intelligence and e-commerce ecosystem-a customer's
perspective. Int. J. Res. Eng. Sci. Manag. 4(2), 78-87 (2021)
How AI marketing can help brands right now
How AI marketing can help brands right now. http://ai4marketing.com/2018/02/
02/ai-marketing-can-help-brands-right-now/. Accessed 19 Sept 2021
Useful eCommerce statistics you must know in 2021
Useful eCommerce statistics you must know in 2021. https://wpforms.com/
ecommerce-statistics/. Accessed 19 Sept 2021
Evolving e-commerce market dynamics
Evolving e-commerce market dynamics. https://www.capgemini.com/wp-content/
uploads/2017/07/evolving_e-commerce_market_dynamics.pdf. Accessed 15 Sept
2021
Inside Facebook's biggest artificial intelligence project ever
Inside Facebook's biggest artificial intelligence project ever. https://fortune.com/
longform/facebook-machine-learning/. Accessed 18 Sept 2021
Good questions, real answers: how does Facebook use machine learning to deliver ads?
Good questions, real answers: how does Facebook use machine learning to deliver ads? https://www.facebook.com/business/news/good-questionsreal-answers-how-does-facebook-use-machine-learning-to-deliver-ads. Accessed 18
Sept 2021
How Amazon quietly powers the internet
How Amazon quietly powers the internet. https://www.forbes.com/sites/
danrunkevicius/2020/09/03/how-amazon-quietly-powers-the-internet/. Accessed
22 Sept 2021
- Aws Ai Explore
- Services
Explore AWS AI services. https://aws.amazon.com/machine-learning/aiservices/. Accessed 22 Sept 2021
Honeywell and Fetch Robotics deliver autonomous mobile robots to DCs
Honeywell and Fetch Robotics deliver autonomous mobile robots to DCs. https://
www.robotics247.com/article/honeywell_partners_with_fetch_robotics_to_
deliver_autonomous_mobile_robots. Accessed 16 Sept 2021
Information Systems Architecture and Technology: System Analysis in Decision Aided Problems
- G Chodak
- J Świątek
- L Borzemski
- A Grzech
Chodak, G.: Genetic algorithms in forecasting of internet shops demand. In:
Świątek, J., Borzemski, L., Grzech, A., Wilimowska, Z. (eds.) Information Systems Architecture and Technology: System Analysis in Decision Aided Problems,
pp. 59-68. Publishing House of the Wrocław University of Science and Technology,
Wrocław (2009)
How Amazon scientists are helping the Scout delivery device find a path to success
How Amazon scientists are helping the Scout delivery device find a path
to success. https://www.amazon.science/latest-news/how-amazon-scientists-arehelping-the-scout-delivery-device-find-a-path-to-success. Accessed 10 Sept 2021
How do AI-based drones work?
How do AI-based drones work? https://heartbeat.fritz.ai/how-ai-based-droneswork-a94f20e62695. Accessed 10 Sept 2021