A highly adaptive recommender system based on fuzzy logic for B2C e-commerce portals

doi:10.1016/j.eswa.2010.08.033

Expert Systems with Applications

Volume 38, Issue 3, March 2011, Pages 2441-2454

https://doi.org/10.1016/j.eswa.2010.08.033 Get rights and content

Abstract

Past years have witnessed a growing interest in e-commerce as a strategy for improving business. Several paradigms have arisen from the e-commerce field in recent years which try to support different business activities, such as B2C and C2C. This paper introduces a prototype of e-commerce portal, called e-Zoco, of which main features are: (i) a catalogue service intended to arrange product categories hierarchically and describe them through sets of attributes, (ii) a product selection service able to deal with imprecise and vague search preferences which returns a set of results clustered in accordance with their potential relevance to the user, and (iii) a rule-based knowledge learning service to provide the users with knowledge about the existing relationships among the attributes that describe a given product category. The portal prototype is supported by a multi-agent infrastructure composed of a set of agents responsible for providing these and other services.

Research highlights

► Electronic Commerce Research and Applications. ► Applications for the development of electronic commerce. ► e-Commerce recommendation applications.

Introduction

The consolidation of the World Wide Web as an everyday technology has allowed the emergence of a new competitive environment where firms can develop or extend their business processes (Kowtha and Choon, 2001, Laudon and Laudon, 2005) to deal with customers from all around the world (Turban, Lee, King, & Chung, 2000). In recent years, the high competitiveness in this environment has caused great research activity focused on developing a new infrastructure aimed at supporting this new business paradigm. This is commonly known as Electronic Commerce (e-commerce), and it can be defined as any business that is electronically transacted (Cameron, 1997). e-Commerce technologies and processes have introduced new ways to do business.

Many business paradigms have arisen from the e-commerce scope. One of the most popular is C2C (Consumer-to-Consumer) e-commerce, where transactions are carried out directly by consumers who negotiate with one another to try to reach an agreement. The main feature that distinguishes C2C from other paradigms arisen from the e-commerce field is that it allows the same individual to play both the seller and the buyer roles in different transactions. One of the first C2C applications to appear, and probably the most popular, is the electronic auction (e-auction), which made possible to overcome the geographical constraints inherent to traditional auctions and allowed any individual to buy or sell goods at any time and from every corner of the world. After the success of C2C, many firms established and started to develop direct shopping activities using this infrastructure, which leaded C2C portals to be used as B2C (Business-to-Consumer) portals. In fact, according to Holahan (2008), the amount of transactions carried out through electronic auctions is slightly decreasing in recent years, whereas the number of direct shopping transactions keeps increasing steadily.

Probably because of the origin of many of the today’s most popular e-commerce portals as e-auctioning sites (C2C), most of them use lexicographic descriptions and objects arrangements to manage their products catalogue. This implies that users must provide the system with key words or text strings denoting a product specific model and/or brand in order to define the search criteria. However, although this approach seems suitable to be used in an auctioning context where consumers are usually looking for very rare and exclusive goods that can be easily indexed through textual descriptions, it does not seem very appropriated to be used under the direct shopping paradigm, due to the following drawbacks: (i) lexicographic searches are prone to return irrelevant results due to the polysemy that many commonly used words have, and (ii) the specification of product features by means of text in description fields makes extremely complex the use of technologies for the automatic comparison and recommendation of products.

Besides, the direct shopping scenario clearly shows the great difference that usually exists in the uncertainty degree in the knowledge of sellers and buyers. That is, whereas sellers usually know well the features of the goods they put up for sale, buyers usually lack of a precise knowledge of what they can find, fact that often leads them to naturally specify what they want in a vague or imprecise way (Klaue, Kurbel, & Loutchko, 2001). Moreover, that lack of knowledge drives consumers to buy the most popular product, although it is possibly not the best nor the most suitable from a quality and cost perspective.

These issues lead us to propose in this work an e-commerce portal focused on the development of direct shopping activities under the B2C paradigm. The main contributions of our work are the following: (i) a hierarchical cataloguing system to arrange products according to a set of features, (ii) a product selection system (search engine) that allows the definition of vague and uncertain search criteria and returns a list of products arranged according to their relevance, and (iii) a recommender system aimed at providing consumers with knowledge about the market that allows them to define more realistic searches and to be aware of what they can buy and at what cost. For these purposes, we propose to use fuzzy logic as tool to deal with the uncertainty and vagueness in the search criteria and to communicate with the users by employing a terminology that is easily understandable for them. Besides, we have taken special care in the resulting portal usability, as this feature usually becomes seriously affected due to the large amounts of data required to specify vague or imprecise search criteria (Castro-Schez, Vallejo-Fernández, Rodriguez-Benitez, & Moreno-García, 2008).

The portal devised in this work is composed of the following components, many of them are commonly found in any current e-commerce portal (C ∣B)2C: a products cataloguing system, a users management system, a messaging system, a products evaluation system, an issues management system, a lexicographic search engine, a sales management system, an auctions management system, a private data management system, and a report generation system.

The remainder of this article is organised as follows. Section 2 reviews some related work relevant to develop our proposal. Section 2.1 describes the architecture of the multi-agent infrastructure that supports the proposed portal. In Section 3, some of the most important portal components are described in detail. These are the cataloguing system in Section 3.1, the product selection system in Section 3.2, and the knowledge learning system in Section 3.3. Section 4 illustrates our proposals by means of a case study. Finally, Section 5 offers a careful discussion and some concluding remarks.

Section snippets

Related work

Many software applications exist nowadays specifically developed to support the necessities of e-commerce, either from the open source community (osCommerce (open source Commerce) e-commerce solutions, 2009, PrestaShip Free Open-Source e-Commerce Software for the Web 2.0, 2009) and from private companies (CubeCart Free& Commercial Online Shopping Cart Solutions, 2009, X-Cart Shopping Cart Software & Ecommerce Solutions, 2009, Zen Cart e-commerce shopping cart software, 2009). Besides, some

Catalogue, product selection, and knowledge learning services

In this section, we devise our proposals for the products management and cataloguing service, the products selection and recommendation service, and the knowledge learning service in detail. These services are provided by the Catalogue and the Product Selection and Recommender agent, respectively.

Case study: searching and selecting the user’s ideal product

This section describes how the e-commerce systems works when a user searches for a desired product o_i. Particularly, this description is focused on the search and selection processes provided by the e-commerce portal that is presented in this paper. The product to be acquired by the user is a digital camera. Within this context, the portal hosts a database with a category named Digital Cameras, which is composed of 119 items. This category is described by means of 51 variables, such as price,

Conclusions

C2C e-commerce web portals became very popular in the last decade due to the popularity reached by some applications, e.g. e-auctions. This fact leaded many companies which developed C2C e-commerce activities to extend their business processes to allow direct shopping activities (B2C) as well, although in many cases they were carried out on the same C2C infrastructure. Soon after, the amount of transactions carried out under the C2C paradigm started to decrease slightly compared to the amount

Acknowledgements

This work has been funded by the Regional Government of Castilla-La Mancha under research projects PII2I09-0052-3440 and PII1C09-0137-6488. The authors would also like to thank Raul Miguel Sabariego for the implementation of the e-Zoco B2C portal prototype.

References (42)

J. Casillas et al.
Mining uncertain data with multiobjective genetic fuzzy systems to be applied in consumer behaviour modelling
Expert Systems with Applications (Springer)
(2009)
J.L. Castro et al.
Learning maximal structure rules in fuzzy logic for knowledge acquisition in expert systems
Fuzzy Sets and Systems
(1999)
J.J. Castro-Schez et al.
Acquiring domain knowledge for negotiating agents: A case of study
International Journal of Human–Computer Studies
(2004)
J.J. Castro-Schez et al.
Using fuzzy repertory table-based technique for decision support
Decision Support Systems
(2005)
W.P. Lee et al.
Intelligent agent-based systems for personalized recommendations in Internet commerce
Expert Systems With Applications
(2002)
E. Mamdani et al.
An experiment in linguistic synthesis with a fuzzy logic controller
International Journal of Man–Machine Studies
(1975)
B.K. Mohanty et al.
Product classification in the Internet business – a fuzzy approach
Decision Support Systems
(2005)
R.R. Yager
Fuzzy logic methods in recommender systems
Fuzzy Sets and Systems
(2003)
L.A. Zadeh
Fuzzy sets
Information and Control
(1965)
L.A. Zadeh
The concept of a linguistic variable and its application to approximate reasoning-I
Information Sciences
(1975)

Agrawal, R., Imielinski, T., & Swami, A. (1993). Mining association rules between sets of items in large databases. In...

Albusac, J., López-López, L. M., Murillo, J. M., & Castro-Schez, J. J. (2008). Supporting customer searches in...

R. Ashri et al.

Architectures for negotiating agents

Lecture Notes in Computer Science (Springer)

(2003)

D. Cameron

The new business platform for the Internet

(1997)

J. Casillas et al.

Fuzzy association rules for estimating consumer behaviour models and its application to explain trust in Internet shopping

Fuzzy Economic Review

(2004)

J.J. Castro-Schez et al.

A fuzzy logic based approach to improve cataloguing and searching in e-commerce portals

Lecture Notes in Business Information Processing (Springer)

(2008)

Foundation for Intelligent Physical Agents....

Foundation for Intelligent Physical Agents, FIPA Agent Management Specification...

Foundation for Intelligent Physical Agents, FIPA Agent Message Transport Service Specification...

M.M. Geipel et al.

A generic framework for argumentation-based negotiation

Lecture Notes in Computer Science (Springer)

(2007)

Hindriks, K. V., Jonker, C., & Tykhonov, D. (2008). Towards an open negotiation architecture for heterogeneous agents....

Cited by (78)

A hybrid similarity model for mitigating the cold-start problem of collaborative filtering in sparse data
2024, Expert Systems with Applications
Similarity is a vital component for neighborhood-based collaborative filtering (CF). To improve the quality of recommendation, many similarity methods have been proposed and analyzed in recent decades. However, nearly all traditional similarity methods and many advanced similarity methods only utilize corated items among users to compute their similarity, which provides limited information in cold-start/sparse scenarios and yields misleading results. In addition, although a few advanced hybrid similarity models consider items beyond corated items, which can partly mitigate the above limitation, they still have drawbacks, such as disregarding penalizing noncorated items that have many disadvantages. In this paper, we explore a new robust hybrid similarity model, namely Wasserstein distance-based CF (WCF) model, for mitigating the cold-start problem of CF in sparse data. Specifically, we measure item similarity via the Wasserstein distance, which can help circumvent the drawbacks in the Bhattacharyya coefficient and KL divergence that are used in the literature, and is thus more robust in a cold-start/sparse scenario. Besides, we further design a new multiplicative user similarity formula which identifies all noncorated items as a whole to prioritize the importance of corated items and impair the negative effects of noncorated items, which will also play an important role in a cold-start/sparse scenario. In addition, we also propose two novel heuristic similarity factors to impair the negative effects of popular users and items as supplements. We conduct extensive experiments on five real-world benchmark recommendation datasets to test WCF. The experimental results show the superiority of WCF over other existing similarity methods in cold-start/sparse scenarios.
Improved recommender systems by denoising ratings in highly sparse datasets through individual rating confidence
2022, Information Sciences
Citation Excerpt :
An increasing number of industries are utilizing RSs to improve user experience and increase user interaction [1]. While a majority of the methods in this area have been proposed to recommend movies [2,3], there have been other studies in areas such as social network [4] applications in markets [5], documents [6], books [7], web search [8], television programs [9], e-commerce [10], e-learning [11] and music [12]. Content-based (CB), collaborative filtering (CF), and hybrid are the most common types of recommender systems in the literature [13–15].
Collaborative filtering (CF) is the most successful approach of Recommender Systems that has been applied in a wide range of applications. In this approach, historical rating data is exploited to calculate similarity between pairs of users and predict user preference over unseen items. The similarity is calculated using users' global preferences estimated from their previous interactions with items. To this end, commonly rated items by a given pair of users are utilized to calculate the similarity. In a sparse dataset, there are limited co-rated items. In addition, inconsistent behaviours of users in rating items may add some noise to data, which makes the ratings more untrustworthy leading to less accuraterecommendations. In this manuscript, we introduce an individual ratings confidence measure (IRC) to calculate the confidence of a given rating to each item by the target user. IRC consists of 5 factors that help to have more information about the interest and boredom of users. User ratings are denoised by prioritizing extreme and high-confidence ratings, and finally, the denoised ratings are used to obtain similarity values. This approach leads to a more accurate neighbourhood selection and rating prediction. We show the superiority of the proposed method when compared with state-of-the-art recommender algorithms over some well-known benchmark datasets.
Improving nonnegative matrix factorization with advanced graph regularization
2022, Information Sciences
Nonnegative Matrix Factorization (NMF) produces interpretable solutions for many applications including collaborative filtering. Typically, regularization is needed to address issues such as overfitting and interpretability, especially for collaborative filtering where the rating matrices are sparse. However, the existing regularizers are typically constructed from the factorization results instead of the rating matrices. Intuitively, we regard these existing regularizers as representing either user factors or item factors and anticipate that a more holistic regularizer could improve the effectiveness of NMF. To this end, we propose a graph regularizer based on a linear projection of the rating matrix, and call the resulting method: Linear Projection and Graph Regularized Nonnegative Matrix Factorization (LPGNMF). We develop two iterative methods to minimize the cost function and derive two update rules named LPGNMF and F-LPGNMF. Additionally, we prove the value of the objective function decreases with LPGNMF and converges to a fixed point with F-LPGNMF. Finally, we test these methods against a number of NMF algorithms on different data sets and show both LPGNMF and F-LPGNMF always achieve smaller errors based on two different error measures.
Understanding consumer preference through fuzzy-based recommendation system
2021, IIMB Management Review
We introduce a new recommendation technique based on fuzzy concepts such as the 2-tuple fuzzy linguistic representation and the fuzzy market research system approach. The recommendation technique uses general consumer perception about product attributes of multi-attributed products such as smartphones as input and gives consumers’ sequential preference of the products as output. The recommendation technique explains the power of an attribute in predicting other attributes, especially in fuzzy and uncertain environments, through the conceptualisation of consumers’ innate associations between the attributes. Our technique provides an understanding of consumer preference through the articulation of buyers’ trade-offs amongst attributes of a product.
A probabilistic graph-based method to solve precision-diversity dilemma in recommender systems
2021, Expert Systems with Applications
Over the last few years, with significant growth of information on the web, users are swamped with a huge amount of information. Recommender system (RS) is an information retrieval technology that aims to provide relevant items to users by considering their preferences. Although several studies in the literature have proposed new RSs to improve the precision of recommendations, some studies have shown that increasing the diversity of recommendations is one way to increase the quality of the user’s experience and to solve the over-fitting problem. While some previous works have tried to make a trade-off between precision and diversity, they could not provide a linear and deterministic trade-off between precision and diversity. As such, these methods are either impractical or infeasible in a real RS. In this paper, we propose a new method to recommend items which are fit to users’ preferences. The method consists of following steps: i) finding users’ preferences using a limited user study, ii) proposing a probabilistic graph-based recommender system (PGBRS) to recommend items with a desirable level of precision and diversity by considering items that are likely to be preferred by the user in the future. PGBRS is a dataset-independent method which is significantly flexible to update with a low implementation complexity.
Personalized digital marketing recommender engine
2020, Journal of Retailing and Consumer Services
Citation Excerpt :
In the process, it collects user preferences of items such as songs, movies, travel destinations, e-learning materials, books, jokes, gadgets, applications, websites and products, and uses an algorithm to make predictions and recommendations based on those items (Bobadilla et al., 2011). This has led to the development of a sizable volume of literature on diversified topics, such as music (Lee et al., 2010; Nanopoulos et al., 2010; Tan et al., 2011), television (Yu et al., 2006; Barragáns-Martínez et al., 2010), books (Núñez-Valdéz et al., 2012; Crespo et al., 2011), documents (Serrano-Guerrero et al., 2011; Porcel et al., 2009, 2010, 2012), electronic-learning (Zaíane, 2002; Bobadilla et al., 2009), electronic commerce (Huang et al., 2007; Castro-Schez et al., 2011), market applications (Costa-Montenegro et al., 2012) and web search (McNally et al., 2011), among others. RE taps into the behaviour of customers who have rated such items (so-called items-rated customers) to make recommendations about what future customers will like most.
E-business leverages digital channels to scale its functions and services and operates by connecting and retaining customers using marketing initiatives. To increase the likelihood of a sale, the business must recommend additional items that the customers may be unaware of or may find appealing. Recommender Engine (RE) is considered to be the preferred solution in these cases for reasons that include delivering relevant items, hence improving cart value, and boosting customer engagement. The paper describes a model for delivering real-time, personalised marketing information concerning the recommended items for online and offline customers, using a blend of selling strategies: up-selling, cross-selling, best-in-class-selling, needs-satisfaction-selling and consultative-selling. The model further defines the e-marketplace by clustering items, customers and unique selling proposition (USP), and then gathering, storing, and processing transactional data, and displaying personalised marketing information to support the customer in their decision-making process, even when purchasing from large item spaces. An experimental study using a quantitative research methodology was conducted in a mid-size healthcare retailer, based out of India, to determine the tangible benefits. The model was tested with 100 online customers and, with the adoption of the proposed methodology, the results indicated growth in average monthly revenue (33.49%), Average Order Value (AOV) (32.79%) and Items per Order (IPO) (1.93%).

View all citing articles on Scopus

View full text

A highly adaptive recommender system based on fuzzy logic for B2C e-commerce portals

Abstract

Research highlights

Introduction

Section snippets

Related work

Catalogue, product selection, and knowledge learning services

Case study: searching and selecting the user’s ideal product

Conclusions

Acknowledgements

Expert Systems with Applications (Springer)

Fuzzy Sets and Systems

International Journal of Human–Computer Studies

Decision Support Systems

Expert Systems With Applications

International Journal of Man–Machine Studies

Decision Support Systems

Fuzzy Sets and Systems

Information and Control

Information Sciences

Architectures for negotiating agents

Lecture Notes in Computer Science (Springer)

The new business platform for the Internet

Fuzzy association rules for estimating consumer behaviour models and its application to explain trust in Internet shopping

Fuzzy Economic Review

A fuzzy logic based approach to improve cataloguing and searching in e-commerce portals

Lecture Notes in Business Information Processing (Springer)

A generic framework for argumentation-based negotiation

Lecture Notes in Computer Science (Springer)