Book Recommender System Using Genetic Algorithm and Association Rule Mining

Hani Febri Mustika; Aina Musdholifah

doi:10.18495/comengapp.v8i2.305

[1] F.Ricci, L.Rokach and B. Shapira, Recommender Systems Handbook, 2nd. ed. New York: Spinger, 2015.
[2] S. Yada, “Development of a book recommendation system to inspire infrequent readers, “ in The Emergence of Digital Libraries – Research and Practices, 2014, pp. 399-404.
[3] P. Jomsri, “Book recommendation system for digital library based on user profiles by using association rule,” in Proceedings of The Fourth Edition of The International Conference on The Innovative, 2014, pp. 130-134.
[4] C. C. Aggarwal, Recommender Systems, New York : Spirnger, 2016.
[5] D.Y. Patil, A.Shekh and G. Kadlag, “Survey on Collaborative Filtering for Digital Libraries,” International Research Jorunal of Enggineering and Technology, vol. 3, issue 12, pp. 1013-1016, December 2016.
[6] K. Tsuji, F. Yoshikane, S. Sato, and H. Itsumura, “Book recommendation using Machine learning methods based on library loan records and bibliographic information,” International Journal of Academic Library and Information Science, vol. 3, pp. 7-23, January 2015.
[7] G.P. Wakure and V. Kadrolli, “Music recommendation system using genetic algorithm,” International Journal of Engineering Research and Technology (IJERT), vol. 2, pp. 580-582, September 2013.
[8] N. Badhe, D. Mishra, C. Joshi, and N. Shukla, “Recommender system for music data using genetic algorithm,” International Journal of Innovations and Advancement in Computer Science, vol. 3, pp. 66-69, April 2014.
[9] D. Jannach M. Zanker, A. Felfernig, and G. Friedrich, An Introduction Recommender Systems, New York: Cambridge University Press, 2011.

Abstract viewed - 1378 times
PDF downloaded - 1652 times

Affiliations

Hani Febri Mustika
Universitas Gadjah Mada

Aina Musdholifah
Universitas Gadjah Mada

Content Top

Book Recommender System Using Genetic Algorithm and Association Rule Mining

Hani Febri Mustika ,
Aina Musdholifah

Vol 8 No 2 (2019)

DOI 10.18495/comengapp.v8i2.305

Submitted: Mar 29, 2019

Published: Jun 11, 2019

Abstract

Recommender system aims to provide on something that likely most suitable and attractive for users. Many researches on the book recommender system for library have already been done. One of them used association rule mining. However, the system was not optimal in providing recommendations that appropriate to the user's preferences and achieving the goal of recommender system. This research proposed a book recommender system for the library that optimizes association rule mining using genetic algorithm. Data used in this research has taken from Yogyakarta City Library during 2015 until 2016. The experimental results of the association rule mining study show that 0.01 for the greatest value of minimum support and 0.4359 for the average confidence value due to a lot of data and uneven distribution of data. Furthermore, other results are 0.499471 for the average of Laplace value, 30.7527 for the average of lift value and 1.91534252 for the average of conviction value, which those values indicate that rules have good enough level of confidence, quite interesting and dependent which indicates existing relation between antecedent and consequent. Optimization using genetic algorithm requires longer execution time, but it was able to produce book recommendations better than only using association rule mining. In Addition, the system got 77.5% for achieving the goal of recommender system, namely relevance, novelty, serendipity and increasing recommendation diversity.