Adjustable discovery of adaptive-support association rules for collaborative recommendation systems

Explainable recommendations enable users to understand why certain items are suggested and, ultimately, nurture system transparency, trustworthiness, and confidence. Large crowdsourcing recommendation systems ought to crucially promote authenticity and transparency of recommendations. To address such challenge, this paper proposes the use of stream-based explainable recommendations via blockchain profiling. Our contribution relies on chained historical data to improve the quality and transparency of online collaborative recommendation filters – Memory-based and Model-based – using, as use cases, data streamed from two large tourism crowdsourcing platforms, namely Expedia and TripAdvisor. Building historical trust-based models of raters, our method is implemented as an external module and integrated with the collaborative filter through a post-recommendation component. The inter-user trust profiling history, traceability and authenticity are ensured by blockchain, since these profiles are stored as a smart contract in a private Ethereum network. Our empirical evaluation with HotelExpedia and Tripadvisor has consistently shown the positive impact of blockchain-based profiling on the quality (measured as recall) and transparency (determined via explanations) of recommendations.

Download Full-text

Cluster searching strategies for collaborative recommendation systems

Information Processing & Management ◽

10.1016/j.ipm.2012.07.008 ◽

2013 ◽

Vol 49 (3) ◽

pp. 688-697 ◽

Cited By ~ 23

Author(s):

Ismail Sengor Altingovde ◽

Özlem Nurcan Subakan ◽

Özgür Ulusoy

Keyword(s):

Recommendation Systems ◽

Collaborative Recommendation

Download Full-text

A COMPARATIVE STUDY AND EVALUATION OF COLLABORATIVE RECOMMENDATION SYSTEMS

10.37099/mtu.dc.etds/807 ◽

2014 ◽

Author(s):

Joshua C. Stomberg

Keyword(s):

Comparative Study ◽

Recommendation Systems ◽

Collaborative Recommendation

Download Full-text

Research on Intelligent Recommendation Method and its Application on Internet Bookstore

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.121-122.447 ◽

2010 ◽

Vol 121-122 ◽

pp. 447-452

Author(s):

Qing Zhang Chen ◽

Yu Jie Pei ◽

Yan Jin ◽

Li Yan Zhang

Keyword(s):

Data Mining ◽

Association Rules ◽

Recommendation System ◽

Recommendation Systems ◽

Experimental Results ◽

Personalized Recommendation ◽

The Internet

As the current personalized recommendation systems of Internet bookstore are limited too much in function, this paper build a kind of Internet bookstore recommendation system based on “Strategic Data Mining”, which can provide personalized recommendations that they really want. It helps us to get the weight attribute of type of book by using AHP, the weight attributes spoken on behalf of its owner, and we add it in association rules. Then the method clusters the customer and type of book, and gives some strategies of personalized recommendation. Internet bookstore recommendation system is implemented with ASP.NET in this article. The experimental results indicate that the Internet bookstore recommendation system is feasible.

Download Full-text

A Study of Association Rules Mining Algorithms Based on Adaptive Support

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.108-111.436 ◽

2010 ◽

Vol 108-111 ◽

pp. 436-440

Author(s):

Yue Shun He ◽

Ping Du

Keyword(s):

Association Rules ◽

Efficient Method ◽

User Needs ◽

Association Rules Mining ◽

Minimum Support ◽

The Core ◽

Minimum Number ◽

Adaptive Support ◽

Mining Algorithms ◽

Specific Number

This paper presents an adaptive support for Boolean algorithm for mining association rules, the Algorithm does not require minimum support from outside, in the mining process of the algorithm will be based on user needs the minimum number of rules automatically adjust the scope of support to produce the specific number of rules, the algorithm number of rules for the user needs to generate the rules to a certain extent, reduce excavation time, avoid the artificial blindness specified minimum support. In addition, the core of the algorithm is using an efficient method of Boolean-type mining, using the logical OR, AND, and XOR operations to generate association rules, to avoided the candidate itemsets generated In the mining process, and only need to scan the database once, so the algorithm has a certain efficiency.

Download Full-text