Shopping Recommender System Research Articles

Fog computing-assisted path planning for smart shopping.

A Smart City (SC) is a viable solution for green and sustainable living, especially with the current explosion in global population and rural-urban immigration. One of the fields that is not getting much attention in the Smart Economy (SE) is customer satisfaction. The SE is a component of SC that is concerned with using Information and Communication Technology (ICT) to improve stages of the traditional economy. In this paper, we propose a fog computing-based shopping recommendation system. Our simulations used Al-Madinah city as a case study. It aims to improve the customer shopping experience. Customers in shopping malls can connect to the system via Wi-Fi. Then the system recommends products to the shoppers according to their preferences. It optimizes shoppers' schedules using price, the distance between the shops, and the congestion. It also improves customers' savings by up to 30%. It also increases the shopping speed by up to 6.12% compared to the system proposed in the literature.

Recommendation System Using Location-Based Services

In today’s world, Technology is a boundary of its own, it continues to change, to expand and to reshape our environment. As technology continues to be explored and extended, more life will change, creating new habits, and forming new ways to work together. Although the future is uncertain, we believe in using technologies to create tailored techniques and solutions.. This evolution of technology is occurring at a rapid pace, and so are the needs and dependencies of people on it. In this paper, our main focus is to expand the e-commerce activities and make them more user friendly by primarily focusing on the location of the user. Thus through this, we are proposing an online shopping recommendation system that detects the current location of the user and recommends him goods that are essential in his/her locality by analysing the needs and demands of those living in his neighbourhood. This subsequently also helps the user to adapt to a new location quickly without having to think much about the essentials as it will be recommended to him by the application.

Research of shopping recommendation system based on improved wide-depth network

With the development of e-commerce, there are more and more commodities. How to recommend the commodities that users are interested in quickly and accurately has become an important research topic in the field of e-commerce.we propose a product recommendation algorithm based on DeepFM network. Firstly, we embed the user’s purchased products, and transform the sparse feature into the low-dimensional dense feature, while the user’s personal attribute features can express the user’s purchase intention to a certain extent, and also use embedded coding to transform the features.DeepFM considers both wide and deep (i.e. low-level and high-level) at the same time to further improve the generalization ability of the model. So we use DeepFM to predict the interest of users in purchasing goods.Learning the expression of user’s interest from user’s purchase and personal preference, so as to accurately predict user’s purchase behavior.Finally, we use the real record data set purchased by online users to evaluate the effect of the model, and compare it with other models to verify the effectiveness of the model.

Critical success factors for Big Data adoption in the virtual retail: Magazine Luiza case study

Purpose – The objective of this research was to identify critical success factors for the adoption of Big Data in the virtual retail, through a case study of Magazine Luiza. The use of Big Data, in this case, focused on improving its system of recommendations for a better understanding of consumer behavior. Design/methodology/approach – The case study was done through interviews, observation of the shopping recommendation system and analyzes of institutional presentations of the Bob project. A semistructured interview script was used in the interviews. Findings – Based on the results, we outline some propositions related to the opportunities and obstacles for the implementation of Big Data in the virtual retail in Brazil. Some of these propositions are in line with what literature, especially BI, has been discussing. However, they still need to be discussed in the context of Big Data. Originality/value – The main contribution of the research was the identification of relevant factors to the adoption of Big Data that were not considered as critical for the adoption of previous technologies.

Personalization and probabilities: Impersonal propensities in online grocery shopping

Accounts of big data practices often assume that they target individuals. Personalization, with all the risks of discrimination and bias it entails, has been the critical focus in accounts of consumption, government, social media, and health. This paper argues that personalization through models using large-scale data is part of a more expansive change in probabilization that, in principle, is not reducible to individual or ‘personal’ attributes and actions. It describes the ‘personalization’ of an online grocery shopping recommender system to list a small number of grocery items of personal relevance for each of the millions of online grocery shoppers at a major UK supermarket chain. Drawing on a theory of probability proposed by the philosopher of science Karl Popper and anthropological work on shopping, it suggests that the attempt to generate personalized predictions necessarily incorporates impersonal relations to others and things. Using a mixture of discourse analysis and code-based reconstruction of key elements of the recommender system, it suggests that personalization is one facet of an open-ended weave of propensities associated with people and things in contemporary big data configurations. The paper explores how, in the context of recommender systems, the constitutive incompleteness of shopping lists, their propensity to expand or change, might be more important than their capacity to be personalized.

A social route recommender mechanism for store shopping support

To survive in a fiercely competitive business environment, it has become increasingly important for physical retailers to provide customers with services offering a better shopping experience. Many renovate and enlarge their shopping spaces to make their stores more enjoyable places to visit. The growth in social media and the use of mobile devices provide retailers with an opportunity to offer a context-aware guidance service to enhance customers' in-store shopping experience. In this research, by extracting and analysing shopping information (shopping context, visiting trajectory) and social information (user's interest, friends' influence), a contextual store shopping recommendation system is proposed to provide an appropriate route for first-time customers or those who are unfamiliar with a retailer's shopping space. Our experimental results show that the proposed model is effective in providing an appropriate shopping route and enhancing users' shopping experience, which could significantly improve the profitability and competitive advantage of the retailers.

EXPLOITING IMAGE CONTENT IN LOCATION-BASED SHOPPING RECOMMENDER SYSTEMS FOR MOBILE USERS

This paper demonstrates how image content can be used to realize a location-based shopping recommender system for intuitively supporting mobile users in decision making. Generic Fourier Descriptors (GFD) image content of an item was extracted to exploit knowledge contained in item and user profile databases for learning to rank recommendations. Analytic Hierarchy Process (AHP) was used to automatically select a query item from a user profile. Single Criterion Decision Ranking (SCDR) and Multiple-Criteria Decision-Ranking (MCDR) techniques were compared to study the effect of multidimensional ratings of items on recommendations effectiveness. The SCDR and MCDR techniques are, respectively, based on Image Content Similarity Score (ICSS) and Relative Ratio (RR) aggregating function. Experimental results of a real user study showed that an MCDR system increases user satisfaction and improves recommendations effectiveness better than an SCDR system.

Mining Skewed and Sparse Transaction Data for Personalized Shopping Recommendation

A good shopping recommender system can boost sales in a retailer store. To provide accurate recommendation, the recommender needs to accurately predict a customer's preference, an ability difficult to acquire. Conventional data mining techniques, such as association rule mining and collaborative filtering, can generally be applied to this problem, but rarely produce satisfying results due to the skewness and sparsity of transaction data. In this paper, we report the lessons that we learned in two real-world data mining applications for personalized shopping recommendation. We learned that extending a collaborative filtering method based on ratings (e.g., GroupLens) to perform personalized shopping recommendation is not trivial and that it is not appropriate to apply association-rule based methods (e.g., the IBM SmartPad system) for large scale prediction of customers' shopping preferences. Instead, a probabilistic graphical model can be more effective in handling skewed and sparse data. By casting collaborative filtering algorithms in a probabilistic framework, we derived HyPAM (Hybrid Poisson Aspect Modelling), a novel probabilistic graphical model for personalized shopping recommendation. Experimental results show that HyPAM outperforms GroupLens and the IBM method by generating much more accurate predictions of what items a customer will actually purchase in the unseen test data. The data sets and the results are made available for download at http://chunnan.iis.sinica.edu.tw/hypam/HyPAM.html.