In today's information-rich society, where users are inundated with vast multi-sourced data, Recommendation system which may focus more on users' lifestyle preferences becomes increasingly significant, especially when providing well-being oriented daily living support. However, it still relies on limited data, overlooking complex relationships between user context, behavior, and item attributes, which often fails to provide truly personalized suggestions, and lifestyle-aware optimization remains underdeveloped. In this study, we propose a Graph Neural Network (GNN)-enhanced Multimodal Fusion with Contrastive Learning model, called GNNMF-CL, which can be applied to pursue high performance in smart systems based on multimodal learning from integrated visual, text, and user's lifestyle information etc. Specifically, a food recommendation system for smart health is designed and built, which extracts visual features using ResNet-50, encodes lifestyle features through contrastive learning based on VLM-generated captions and nutritional information, and captures taste preference features via Graph Attention Network (GAT). In addition, a Heterogeneous Graph Transformer (HGT) is developed to improve the multimodal feature fusion, and the five loss functions are defined to jointly optimize high-order neighborhood relations and ranking of recommended items in model training. Experiments and evaluations on the AllRecipes dataset demonstrate that our proposed model significantly outperforms other existing methods, in achieving high performance recommendations that align with users' health goals and contribute to broader applications in the smart health domain.

The rapid development and usage of digital technologies in modern intelligent systems and applications bring critical challenges on data security and privacy. It is essential to allow cross-organizational data sharing to achieve smart service provisioning, while preventing unauthorized access and data leak to ensure end users’ efficient and secure collaborations. Federated Learning (FL) offers a promising pathway to enable innovative collaboration across multiple organizations. However, more stringent security policies are needed to ensure authenticity of participating entities, safeguard data during communication, and prevent malicious activities. In this paper, we propose a Decentralized Federated Graph Learning (FGL) with Lightweight Zero Trust Architecture (ZTA) model, named DFGL-LZTA, to provide context-aware security with dynamic defense policy update, while maintaining computational and communication efficiency in resource-constrained environments, for highly distributed and heterogeneous systems in next-generation networking. Specifically, with a re-designed lightweight ZTA, which leverages adaptive privacy preservation and reputation-based aggregation together to tackle multi-level security threats (e.g., data-level, model-level, and identity-level attacks), a Proximal Policy Optimization (PPO) based Deep Reinforcement Learning (DRL) agent is introduced to enable the real-time and adaptive security policy update and optimization based on contextual features. A hierarchical Graph Attention Network (GAT) mechanism is then improved and applied to facilitate the dynamic subgraph learning in local training with a layer-wise architecture, while a so-called sparse global aggregation scheme is developed to balance the communication efficiency and model robustness in a P2P manner. Experiments and evaluations conducted based on two open-source datasets and one synthetic dataset demonstrate the usefulness of our proposed model in terms of training performance, computational and communication efficiency, and model accuracy, compared with other four state-of-the-art methods for next-generation networking security in modern distributed learning systems.

The pandemic of COVID-19 reminds us of the basic important principles for prevention of infection: avoid the "Three Cs": closed spaces, crowded places and close contact settings. Outpatient clinics in Japan are typical examples of three Cs, where some kinds of decision support system are required to solve the above situation. This paper proposes data mining based patient navigation support system to prevent the Three Cs. Behind the systems, temporal data mining units plays an important role in providing temporal information to the patients, such as waiting time and human densities in the waiting rooms. It analyzes the data stored in hospital information systems, including patient information, logs of clinical orders. The analysis results show that several aspects of patients’ waiting are visualized by temporal data mining.

This paper proposes a novel approach of in-store route data obtained by RFID for customer segmentation based on process mining (PM). The PM technique can dig out the hidden information of customers' in-store shopping route deeply. Firstly, we use PM to customize and decompose consumers' in-store movement paths. Then, we divide the fish area into patterns, and define these patterns as passing area, staying area and entering area respectively. Finally, we decompose the customer’s shopping path into several sub-processes according to the customer’s moving sequences obtained by RFID technology. In the experiment, we use the K-mediods algorithm based on Levenshtein distance to classify and analyze the characteristics of consumer moving path process logs, and investigate correlation analysis of different types of consumers obtained by analyzing the consumers' in-store movement paths through PM technology will be carried out.

In this article, we use the method of machine learning to model the consumer behavior, in order to identify the consumers with high volume purchases, and make a quantitative analysis of their behavior patterns. Firstly, radio frequency identification (RFID) sensors are installed in physical supermarkets for data sampling, tracking the shopping behavior of consumers in supermarkets, combining them with point of sale (POS) data at checkout, and transferring them to consumer behavior data set. Then, based on POS data, we mark consumers as high volume, low volume and none volume customer groups with historical purchase volume as target variables. Based on RFID data, stay time, shopping background, flow direction and number of return visits are extracted as explanatory variables. In the experiment, a classification model of consumer behavior is established by using long short-term memory based neural network (LSTM-NN). Numerical experiments show that LSTM-NN has higher recognition accuracy than logistic regression and support vector machine, which are improved by 5.26% and 6.97% respectively.

The purpose of this study is to clarify the effects of visual complexity and consumer's experience on visual attention and purchase behavior. Data on visual attention collected by using eye tracking has been applied to investigate the effects of advertisement design and consumer's attributes. However, it is difficult to analyze the effects of various factors on visual attention and purchase behavior because they have complicated relations. This study uses visual complexity as a factor of visual stimuli affecting visual attention and purchase behavior. Moreover, consumer experience is applied as an attribute of consumers. Experience is understood to be a factor that strongly impacts purchase behavior. This study applies path analysis for clarifying the relationships among these factors. Eye tracking data collected on catalog mail order shopping was used to clarify the relationship among visual complexity, consumer experience, visual attention, and purchase behavior.

The purpose of this research is to clarify what impact the regulatory resources of the customer have on search behavior and the resultant search benefit. Regulatory resources of the customer engendered by failure of self-control on the part of the customer change along with the string of purchase decisions made in-store. This paper examines the impact of these changes on search behavior in order to present suggestions for more efficient business. It also clarifies the fact that there are differences in search behavior and search benefits depending on the customer and their varying regulatory resources. Discoveries made in this research are provided to store managers as key suggestions on layout, in-store promotions, and strategic pricing for product categories.

The purpose of this study is to develop a new method for handling social influence in the analysis of shopping path data by using the ecological system of ants. Social influence which shoppers effect on each other is believed to contained in shopping path data collected in a retail store. The existing study measured social influence by using “density” which is the number of shoppers in a sales section at a certain point. However, the obtained result differed from the hypothesis of social influence in marketing area. One reason of this result is guessed that the density is calculated with considering temporal variation of social influence at the sales section. This study reviews the result of existing study by measuring social influence by using the concept of pheromone which has a close relationship with ants’ social behaviors. In this paper, the availability of the proposed definition of social influence is examined by focusing on sales sections with large variance of criteria.

Given the prevalence of loyalty programs' implementation in service industries, in order to create a difference in the eyes of the customer from other competitors, examining new loyalty program designs become more and more important for most firms. Compare with Zhang and Breugelmans' research of the item-based loyalty program (IBLP), this research studies a more complicated IBLP design, in which customers can earn different extra points for purchases made on different items. The main purpose of this research is to examine the short-term impact of items with different points in this new IBLP design on different types of customers' purchase behavior. Using data from a Japanese grocery store chain, this study shows that those customers who were heavy customers at the beginning of the IBLP are more affected by this new IBLP design. Then, instead of higher-point items, a middle-level-point, 25-point items has the highest impact on customers' purchase behavior. These findings suggest this special tactic can enhance the value of firm's loyalty program, and help managers to further improve the effect of the IBLP by arranging more targeted items to different types of customers.

Price promotions as a marketing tool can effectively attract customers to buy products impulsively. However, when customers are in the face of price promotions, their self-control also emerges. Their desire to consume collides with their self-control, which will react differently to vice and virtue category products. In order to figure out the relationship among self-control, price promotions and consumer purchase behavior, this paper uses shopping path and POS data to study customers' shopping and buying behaviors in stores. Through logistic regression analysis, we verified how self-control and price promotions affected customers' purchase process. Then we found that customers would be more likely to purchase vice category products with price promotion when they stayed in a store for a certain period. This paper is the first one to empirically study the effect of both self-control and price promotions on customers' purchase behavior of vice category products. It can provide market managers with a better understanding on customers' purchase behavior and a more effective way to increase sales.

Customer relationship management (CRM) is one of the most important recommendation systems to manage customer groups and understand potential relationships. CRM systems use many communication approaches such as telephone, email and social media to collect mass of customer data, which can help the companies (managers) to increase sales growth and enhance customer retention. Since 2000s, the advancements of RFID technology brought a new perspective on customer in-store behavior. Based on such RFID data, this paper describes a novel analytic approach applying social network analysis (SNA) into customer relationship network (CRN) and presents three contributions. First, to be different from existing studies, we attempt to construct the CRN based the shopping path (visiting patterns), which is recognized as a data stream of digitally encoded coherent signals. The CRN can help us to understand the customer relationships from the network perspective. Second, we employ network clustering (also called community detection or node classification) method to extract customer groups by maximizing the modularity. The modularity provides us a structural and relational understanding of customer groups. Third, we use within-module agree and participant coefficient to measure how a customer well-connected to other customers in the CRN; and identify such customers as "hub" customers by a topological process.

Recent years have seen active research that utilizes information combining geographic data and sensor data, called geospatial information, in urban planning, medical care and marketing. In this study, we focus on RFID technology that records position information (i.e., spatial information) of shopping carts in a supermarket, and estimate the latent space-time structure of the store as observation data of customers’ visits. Then, we propose a dynamic Bayesian model for sales analysis, which extends the conventional state-space model to include the spatiotemporal structure. From the results of the model analysis, it is obvious that supermarkets have clear periodic structures in units of time periods and weekly structures, and they are dynamically related to the adjacency of each sales area. By utilizing the visualization of the space-time structure of the sales area, it is possible to easily inform the store manager about the influence of customers’ visits on sales outcomes.

The purpose of this study is to clarify the applicability of data-driven approach in accounting area. As the first stage, focusing on the model comparison, this paper shows the effectiveness of model selection with data mining technique for the development of earnings prediction model based on financial statement data. In accounting area, researchers have not considered the characteristic of financial statement data and a suitable method for that enough. In this study, several methods are applied to develop prediction models. From the comparison with obtained results, we discuss the characteristic of financial statement data and show the possibility of data mining technique for the improvement of prediction accuracy.

The purpose of this study is to verify the effectiveness of a data-driven approach for financial statement analysis. In the area of accounting, variable selection for construction of models to predict firm's earnings based on financial statement data has been addressed from perspectives of corporate valuation theory, etc., but there has not been enough verification based on data mining techniques. In this paper, an attempt was made to verify the applicability of variable selection for the construction of an earnings prediction model by using recent data mining techniques. From analysis results, a method that considers the interaction among variables and the redundancy of model could be effective for financial statement data.

This paper aims to use fractal dimensions to quantify the complexity of customer in-store movements, and proposes a purchase model factoring in the effects of complex customer movements on purchase behavior. We used the box-counting method to calculate the fractal dimension of shopping paths and investigated its relationships with basket size and sales, which are viewed as important for marketing. We found that the customer group with high fractal dimensions had mean values for the number of sales floor zones visited, basket size, stay time in store, and sales amount statistically higher than those of the customer group with lower fractal dimensions. We analyzed a binomial logit model to identify positive effects that the fractal dimension has on purchases in the food ingredient categories of vegetable, fish, and meat.

Abstract. Data about the shopping paths of customers in stores are now available due to developments in radio frequency identifica- tion technology. In this study, we conducted clustering of the shopping paths of customers gathered in a grocery store in Japan. We obtained nine typical movement patterns from the clustering results. In addition, we associated the customers’ shopping paths with purchase results obtained from point of sales data. We examined the movement patterns in terms of their demographic features, purchase results, stay time ratio for each sales area, and the shapes of the movement patterns.

The purpose of this article is to verify the effect of previous purchases on later purchases, using shopping path data. We focus on the effect of vice category products bought before. In existing research, the effect of the prior purchase of virtue category products (which are relative necessities) on later purchases, is explained as licensing effect. Based on earlier studies, the purchase of vice category products is also expected to impact later purchase behavior. For example, prior vice category products purchased may impel customers to purchase virtue category products. But the verification result clearly indicated that prior purchase of vice category products did not impel customers to buy virtue category products, rather it indirectly led to a tendency to refrain from further purchases of products.

The purpose of this research paper is to render the customer-shopping path and customer existence probability visible such that people in the marketing field can easily grasp customer behaviors in store. To achieve this, we introduced the customer existence probability, which provides a visual of how long customers stay in each sales floor zone. The visualization system was then applied to customer-shopping path data to provide separate and concurrent displays of customer-shopping paths and the customer existence probability. Concurrent display of customer-shopping paths/customer existence probability is suitable for visualization of longer customer stays in-store, where the customer moves a great deal. This display enables easy assessment of in-store customer rounds including length of time. It also incorporates to the maximum the information volume of customer-shopping path data.

In grocery stores, large-scale transaction data with identification, such as point of sales (POS) data, is being accumulated as a result of the introduction of frequent shopper programs. We propose two recommendation systems based on transaction data of a grocery store. In recommending product items in grocery stores, data sparsity is a problem. This is because individual customers only purchase very few of the total number of product items a store sells. We evaluate various recommendation methods including SVD-type recommendation based on real POS data and summarize methods suitable for the proposed recommendation systems.

Basic necessities are generally said to be price inelastic in comparison with luxury goods. However, within the former group, it is not easy to differentiate between milk products using factors other price. Therefore, price could be an important factor when deciding between milk products. In this study, we verify the hypothesis that milk products are price elastic based on customer transaction data. If milk products are non-elastic in terms of price, we consider that people's choice of brand is decided by factors other than price, such as brand loyalty, which we then evaluate using a multinomial logit model.

Consumers classification is one of the most important task in the retail sector. RFID (Radio Frequency IDentification) - A wireless non-contact technology is made easier to classify the consumers’ in-store behavior, recently. This paper presents an extraction of consumer purchasing behavior using statistical learning theory SVM (Support Vector Machine). In this research, we present our recent investigation outcome on the consumers shopping behavior in a Japanese supermarket using RFID data. We observe that it is possible to express the individual difference of consumers how are they spending time (we call it stay time in this paper) on shopping in a certain area of the supermarket. The contribution of this research is in two folds: we employ a SVM model on dealing with the RFID data of the consumer in-store behaviour firstly, as compared with other forecast model such as linear regression analysis and bayesian network, SVM provides a significant improvement in the forecasting accuracy of purchase behaviour (from 81.49% to 88.18%). Secondly, the kernel trick is adopted inside the SVM theory to choose the appropriate kernel for consumer purchasing behavior extraction.

This paper represents our recent studies about the prediction of purchase behavior and an advancement of in-store behavior with respect to RFID technology. In contrast to prior innovators in this research field, this paper has paid special attention to stay time spent on shopping in a target area rather than the whole supermarket, which can serve us to interpret the decision process of purchasing one product or a series of products in a much more intuitive and precise measurement. Also, we develop an integrated model to combine purchase behavior and in-store behavior. A probabilistic graphical model - bayesian network is employed to demonstrate a quantitative analysis process of purchase behavior decision over stay time. In order to distinguish purchase intention among different customers, an attitudinal factor - purchase background of customer is introduced in this paper to build bayesian network. As bayesian network can only deal with the discrete variables, a clustering algorithm is applied to discretize the continuous variables. In the experiments, the optimal cluster number of stay time and purchase background is examined for maximizing the performance evaluation with higher accuracy, and the results also show bayesian network has a better accuracy than other typical prediction models. Finally, we investigate the sensitivity and specificity of purchase behavior predicted by our proposal in adjustment of decision threshold, and use ROC (Receiver Operating Characteristic) curve to determine the optimal decision threshold which can maximize the classification accuracy of models.

Thanks to the advancement of tracking technologies such as RFID (Radio Frequency Identification) in recent years, the study area of shopping behavior of consumers in retailing setting has globally regained increased interest. However, only few studies have attempted to analyze consumer shopping behavior using the RFID data. In this paper we postulate the hypotheses which can be tested using RFID data. This paper aims to contribute to the understanding of the impact of neurophysiologic (human) and environmental (store layout) variables on walking and shopping behavior, by conducting the literature review related to orientation of customers in retailing space. It proposes a framework that addresses the relationship between two types of variables; and builds up three main hypotheses related to their different facets. Finally, the managerial implications are also proposed based on the developed framework.

Because of developments in Radio Frequency Identification (RFID) technology, data about customers’ movement paths in the grocery store are now available. In this paper, we propose a customer behavior model in the grocery store using RFID data. The proposed model is based on a nonhomogeneous hidden Markov model with covariates, and “Stop” and “Pass by” behaviors are estimated. The purchase probability of each behavior is confirmed, and we find that customers often purchase with high probability when the behavior is “Stop.” In addition, we examine the influence of sales areas and bargain sales on customer behavior by using these variables as covariates. We find that certain sales areas have strong effects on the “Stop” behavior. We confirm that these sales areas are arranged along the perimeter of the store or in the central aisle; the obtained knowledge corresponds to empirical knowledge.

Due to developments in technology, movement data tracking a customer's movements in a supermarket in addition to conventional POS data are now available. A problem in analyzing such data is that an ordinary statistical model assuming customer homogeneity does not fit well to such data. In this article, we propose a framework for analyzing such data in a collection of supermarket departments. The framework is based on the mixture regression model assuming the customers' heterogeneity. By the model, we find the latent homogenous groups of the customers and explain the number of items by a stationary time based on the regression model in each latent group. The method of the mixture regression model is explained in addition to the estimation method. We found that a small number of the customers buy more items by going to the supermarket departments and are more sensitive to the stationary time, while a large number of the customers buy less and are less sensitive.

The sensor network technology developed in recent years has made it possible to accurately track the in-store behavior of customers which was previously indeterminable. The information on the in-store behavior of customers obtained by using this technology, namely information on their shopping path, provides us with useful information concerning the customer’s purchasing behavior. The purpose of this research is to apply character string analysis techniques to shopping path data so as to analyze customers’ in-store behavior, and thereby clarify technical problems with them (the character string analysis techniques) as well as their usability. In this paper we generated character strings on visit patterns to store sections by focusing exclusively on customers stopping by these sections in order to elucidate the visiting patterns of customers who made a large quantity of purchases. In this paper, we were able to discover useful information by using the character string analysis technique EBONSAI, thereby illustrating the usability and usefulness of character string analysis techniques in shopping path analysis.

The purpose of this study is to introduce a case study on the application of data mining technology to the matter of pricing in business, and to clarify the latent risks contained in that process. In this paper, we have used data mining technology to analyze the purchase history data of customers for the purpose of discovering the price pattern that maximizes store profits. We describe the processes from data analysis to implementing a business plan, and we consider the risks involved in the business application of data mining.

In this research, we discuss the business application of process data, being the massive accumulated time series of changing conditions. Unlike the data resulting from daily operations, process data includes rich information on operational processes. It is unstructured and becomes massive in scale. In this paper, we introduce a project in which we participated, designed to utilize such process data in business. We also examine the lessons learned from this case study.

It is difficult to carry out quantitative measurements of the persuasive power of business communications (i.e., persuasive skills) and such communications are likely to involve difficult to understand, unseen and unknown knowledge. However, using unstructured recorded communication data based on conversations with business customers, we have been developing explicit knowledge concerning skills necessary for effective communications in the form of an expression framework. The objective of this research is to generate a framework and a process for explicit management knowledge concerning understandable communication skills as opposed to the tacit, hard to understand the negotiating skills related to overdue payment collection personnel and to verify the actual usefulness of this knowledge using the accumulated data in a company. Using this process we have developed, it is possible to discover the special characteristics of the communication content of high success overdue payment collection personnel.

The purpose of this paper is to introduce a process for implementing optimal pricing that uses PRISM to maximize store profits. PRISM is a system and process that uses data mining technology to process large volumes of data, then develops a probability model for customer purchases, and which then uses a heuristic approach to identify the pricing pattern that will maximize store profits. For this paper, we used customer purchase data from Japanese supermarkets to identify the optimal pricing pattern for curry roux, which would maximize store profits.