A rough set-based association rule approach for a recommendation system for online consumers
Graphical abstract
Section snippets
Research background
Most online businesses that are involved in the sales of products/services, such as commercial websites, are aware of the need to acquire knowledge about their online consumers. However, knowledge about online consumers, though available, is not accessible, so it is critical to analyze all of the available knowledge if online users in search for information, products, or services and then highlight potential product promotions and marketing alternatives from online firms. In this regard,
Recommendation systems
Since the development of the first recommendation system by Goldberg, Nichols, Oki, and Terry (1992), various recommendation systems and related technologies, such as CBF and CF, have been reported (Herlocker et al., 2004, Zenebe and Norcio, 2009). Of these, user-based CF is considered to be the most successful recommendation technique and is successfully used by many e-commerce systems, such as Amazon.com and Dell.com (Konstan et al., 1997). CF elicits superior preference information from the
Methodology – the rough set-based association rule approach
In terms of developing rough set and association rules for a recommendation system, this study proposes a rough set based association rule approach that is developed from ordinal data scale processing for customer preference analysis. The proposed analysis approach generates rough set attribute functions, association rules and their modification mechanism. The steps for developing the algorithms that are involved in the proposed approach are as follows:
Step 1: Data processing — create a data
Proposing recommendation system for online shopping platforms
In the regard of experimental design on proposing recommendation system, by using the AHP rough set-based association rule approach, this study implements a recommendation system for Internet shopping portals by determining online consumer purchase preferences using a questionnaire survey. A total of 850 questionnaires were distributed and 720 questionnaires were returned, including 707 effective questionnaires. Nominal and ordinal scale questions were used. The questionnaire contained four
Behavioral change due to recommendation systems
In the regard of experimental design on changing customer behavior, this study also determines whether consumers accept the recommendation results that are generated by the proposed approach and whether they then change their purchase behaviors. Using the same subjects as the previous numerical example, the conditions for acceptance of the recommendations on an Internet portal and product category are determined. A total of 850 questionnaires were sent and 698 questionnaires were returned,
Conclusion
As business assets, consumers play a vital role in marketing. Most of the parties involved in product sales, such as commercial web sites, retailers and channels, are aware of the need for businesses to acquire and share better customer knowledge. However, the opportunities are limited because knowledge about customers is available but not accessible, and there is little possibility of fully analyzing all of the data that must be collected. The effective processing and use of data has become
Acknowledgements
This research was funded by the Ministry of Science and Technology, Taiwan, Republic of China (MOST 103-2410-H-032-043-MY3).
References (49)
- et al.
A rough set model with ontologies for discovering maximal association rules in document collections
Knowledge-Based Systems
(2003) - et al.
An anticipation model of potential customers’ purchasing behavior based on clustering analysis and association rules analysis
Expert Systems with Applications
(2007) - et al.
Mining customer product ratings for personalized marketing
Decision Support Systems
(2003) - et al.
Applied behavioral economics and consumer choice
Journal of Economic Psychology
(2003) - et al.
Rough sets theory for multicriteria decision analysis
European Journal of Operational Research
(2001) A personalized recommendation system based on product taxonomy for one-to-one marketing online
Expert Systems with Applications
(2005)- et al.
Maximizing customer satisfaction through an online recommendation system: A novel associative classification model
Decision Support Systems
(2010) - et al.
Using information retrieval techniques for supporting data mining
Data & Knowledge Engineering
(2005) - et al.
Integration of ART2 neural network and genetic K-means algorithm for analyzing Web browsing paths in electronic commerce
Decision Support Systems
(2005) - et al.
Interpreting the web-mining results by cognitive map and association rule approach
Information Processing & Management
(2011)
Interest-based real-time content recommendation in online social communities
Knowledge-based Systems
Mining customer knowledge for direct selling and marketing
Expert Systems with Applications
Mining customer knowledge for exploring online group buying behavior
Expert Systems with Applications
A hybrid of sequential rules and collaborative filtering for product recommendation
Information Sciences
A cognitive approach for agent-based personalized recommendation
Knowledge-based Systems
Incorporating group recommendations to recommender systems: Alternatives and performance
Information Processing & Management
Rough sets and intelligent data analysis
Information Sciences
Rough sets and Boolean reasoning
Information Sciences
Employing rough sets and association rule mining in KANSEI knowledge extraction
Information Sciences
Enhancement of information seeking using an information needs radar model
Information Processing & Management
Personalized rough-set-based recommendation by integrating multiple contents and collaborative information
Information Sciences
A personalized route recommendation service for theme parks using RFID information and tourist behavior
Decision Support Systems
A personalized recommender system for the cosmetic business
Expert Systems with Applications
Website browsing aid: A navigation graph-based recommendation system
Decision Support Systems
Cited by (51)
Time matters: Investigating the asymmetric reflection of online reviews on customer satisfaction and recommendation across temporal lenses
2024, International Journal of Information ManagementA novel approach for spam detection based on association rule mining and genetic algorithm
2022, Computers and Electrical EngineeringInvestigating sports behaviors and market in Taiwan for sports leisure and entertainment marketing online recommendations
2021, Entertainment ComputingCitation Excerpt :Lately, data mining tends to refer to the use of predictive analytics, user behavior analytics, or certain other advanced data analytics methods that extract value from data, and seldom to a particular size of data set [33]. In the regard of data analysis and computation, data mining approach, is a relatively recent process for the discovery of significant knowledge, such as patterns, associations, changes, anomalies, clustering and significant structures, from large amounts of data that is stored in databases, data warehouses, or other information repositories [34–37]. For example, Wicker and Breuer [38] explored the critical determinants of these organizational problems.
Investigating online social media users’ behaviors for social commerce recommendations
2021, Technology in SocietyMachine learning through the lens of e-commerce initiatives: An up-to-date systematic literature review
2021, Computer Science ReviewCitation Excerpt :However, there are two different approaches to this profit: (i) by the sellers, where the goal is to increase the sale value, or; (ii) by the customer, where the profit is attempted through minimizing fraudulent operations. Recommendation systems [28,31,33,39,40,51,57,59,60,65,72,75,77,78,80,83] aim to increase the sales value trying to recommend other products that the customer may be interested in, causing the average cost of the cart to improve when the system can suggest a new product that the customer is interested in. Regarding the category of fraud detection [21,25,34,38,41,46,52,53,55,82,86], the attempt of profit is on the part of the user.
Rule-based machine learning for knowledge discovering in weather data
2020, Future Generation Computer SystemsCitation Excerpt :However, it is needed to provide a thorough and detailed analysis of the correlation that exists between involved measures, and to offer credible suggestions for domain actors for the evaluation of their models with possible avenues for reflection [14]. It is more and more important to understand the correlations between data, and data mining methods, which are interesting to find some patterns and association rules for various analyses and decision aids such as product category recommendations and determination of possible behavioral changes [15]. As part of the investigation of extreme weather events, Chang presented an innovative data analysis for weather using Cloud Computing, integrating both application services and Data Science services [16].