Accuracy Assessment of Similarity Measures in Collaborative Recommendations Using CF4J Framework

Full Text (PDF, 1252KB), PP.41-53

Views: 0 Downloads: 0

Author(s)

Vijay Verma 1,* Rajesh Kumar Aggarwal 1

1. Computer Engineering Department, National Institute of Technology, Kurukshetra, Haryana, India-136119

* Corresponding author.

DOI: https://doi.org/10.5815/ijmecs.2019.05.05

Received: 7 Mar. 2019 / Revised: 15 Mar. 2019 / Accepted: 21 Mar. 2019 / Published: 8 May 2019

Index Terms

Recommender Systems, Collaborative Filtering, Similarity Measures, CF4J Framework

Abstract

There are various libraries that facilitate the design and development of recommender systems (RSs) research in both the academia and industry. Different libraries provide a different set of functionalities based on their foundational design principles. When new algorithms are proposed, researchers need to compare these against prior algorithms considering many challenges such as reproducibility of results, evaluation metrics, test harnesses, etc. Although many open source RS libraries exist to carry out research experiments and provide a varying degree of features such as extensibility, performance, scalability, flexibility, etc. To that end, this paper describes a recently introduced open-source RS library, Collaborative Filtering for Java (CF4J), which is specially designed for collaborative recommendations. Firstly, the brief internals of the CF4J framework are explained and it has been compared with other related libraries such as LibRec, LensKit, and Apache Mahout based on the recommendation approaches and evaluation tools. Secondly, we have summarized all the state-of-art similarity measures provided by the CF4J library. Finally, in order to determine the accuracy of these similarity measures, several experiments have been conducted using standardized benchmark datasets such as MovieLens-1M, MovieLens-10M, and MovieLens-20M. Empirically obtained results demonstrate that the Jaccard-Mean Squared Difference (JMSD) similarity measure provides better recommendation accuracy among all similarity measures.

Cite This Paper

Vijay Verma, Rajesh Kumar Aggarwal, "Accuracy Assessment of Similarity Measures in Collaborative Recommendations Using CF4J Framework", International Journal of Modern Education and Computer Science(IJMECS), Vol.11, No.5, pp. 41-53, 2019.DOI: 10.5815/ijmecs.2019.05.05

Reference

[1]G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions,” IEEE Trans. Knowl. Data Eng., vol. 17, no. 6, pp. 734–749, 2005.
[2]J. Bobadilla, F. Ortega, A. Hernando, and A. Gutiérrez, “Recommender systems survey,” Knowledge-Based Syst., vol. 46, pp. 109–132, 2013.
[3]K. Lang, “NewsWeeder : Learning to Filter Netnews ( To appear in ML 95 ),” Proc. 12th Int. Mach. Learn. Conf., 1995.
[4]C. Science and J. Wnek, “Learning and Revising User Profiles: The Identification of Interesting Web Sites,” Mach. Learn., vol. 331, pp. 313–331, 1997.
[5]W. Hill, L. Stead, M. Rosenstein, and G. Furnas, “Recommending and evaluating choices in a virtual community of use,” in Proceedings of the SIGCHI conference on Human factors in computing systems - CHI ’95, 1995.
[6]U. Shardanand and P. Maes, “Social information filtering: Algorithms for Automating ‘Word of Mouth,’” Proc. SIGCHI Conf. Hum. factors Comput. Syst. - CHI ’95, pp. 210–217, 1995.
[7]R. Burke, “Hybrid recommender systems: Survey and experiments,” User Model. User-Adapted Interact., 2002.
[8]Billsus Daniel and Pazzani Michael J., “User modeling for adaptative news access,” User Model. User-adapt. Interact., vol. 10, pp. 147–180, 2002.
[9]X. Su and T. M. Khoshgoftaar, “A Survey of Collaborative Filtering Techniques,” Adv. Artif. Intell., vol. 2009, no. Section 3, pp. 1–19, 2009.
[10]M. D. Ekstrand, “Collaborative Filtering Recommender Systems,” Found. Trends® Human–Computer Interact., vol. 4, no. 2, pp. 81–173, 2011.
[11]Y. Shi, M. Larson, and A. Hanjalic, “Collaborative Filtering beyond the User-Item Matrix : A Survey of the State of the Art and Future Challenges,” ACM Comput. Surv., vol. 47, no. 1, pp. 1–45, 2014.
[12]J. S. Breese, D. Heckerman, and C. Kadie, “Empirical analysis of predictive algorithms for collaborative filtering,” Proc. 14th Conf. Uncertain. Artif. Intell., vol. 461, no. 8, pp. 43–52, 1998.
[13]D. Joaquin and I. Naohiro, “Memory-Based Weighted-Majority Prediction for Recommender Systems,” Res. Dev. Inf. Retr., 1999.
[14]A. Nakamura and N. Abe, “Collaborative Filtering Using Weighted Majority Prediction Algorithms,” in Proceedings of the Fifteenth International Conference on Machine Learning, 1998, pp. 395–403.
[15]D. Billsus and M. J. Pazzani, “Learning collaborative information filters,” Proc. Fifteenth Int. Conf. Mach. Learn., vol. 54, p. 48, 1998.
[16]T. Hofmann, “Collaborative filtering via Gaussian probabilistic latent semantic analysis,” Proc. 26th Annu. Int. ACM SIGIR Conf. Res. Dev. information Retr. - SIGIR ’03, p. 259, 2003.
[17]L. Getoor and M. Sahami, “Using probabilistic relational models for collaborative filtering,” Work. Web Usage Anal. User Profiling, 1999.
[18]B. Marlin, “Modeling User Rating Profiles for Collaborative Filtering,” in Proceedings of the 16th International Conference on Neural Information Processing Systems, 2003, pp. 627–634.
[19]D. Pavlov and D. Pennock, “A maximum entropy approach to collaborative filtering in dynamic, sparse, high-dimensional domains,” Proc. Neural Inf. Process. Syst., pp. 1441–1448, 2002.
[20]K. Laghmari, C. Marsala, and M. Ramdani, “An adapted incremental graded multi-label classification model for recommendation systems,” Prog. Artif. Intell., vol. 7, no. 1, pp. 15–29, 2018.
[21]“Duine Framework - Recommender Software Toolkit.” [Online]. Available: http://www.duineframework.org/. [Accessed: 23-Feb-2019].
[22]“Cofi: A Java-Based Collaborative Filtering Library.” [Online]. Available: http://www.nongnu.org/cofi/. [Accessed: 10-Feb-2019].
[23]“easyrec : open source recommendation engine.” [Online]. Available: http://www.easyrec.org/. [Accessed: 23-Feb-2019].
[24]J. Lee, M. Sun, and G. Lebanon, “PREA : Personalized Recommendation Algorithms Toolkit,” J. Mach. Learn. Res., vol. 13, pp. 2699–2703, 2012.
[25]Z. S. and N. Y.-S. Guibing Guo, Jie Zhang, “LibRec: A Java Library for Recommender Systems,” Proc. 23rd Conf. User Model. Adapt. Pers., vol. 2, pp. 2–5, 2015.
[26]S. Schelter and S. Owen, “Collaborative Filtering with Apache Mahout,” Recomm. Syst. Chall. ACM RecSys, vol. I, 2012.
[27]C. E. Seminario and D. C. Wilson, “Case study evaluation of mahout as a recommender platform,” CEUR Workshop Proc., vol. 910, no. Rue, pp. 45–50, 2012.
[28]M. D. Ekstrand, M. Ludwig, J. A. Konstan, and J. T. Riedl, “Rethinking the Recommender Research Ecosystem : Categories and Subject Descriptors,” Proc. 5th ACM Conf. Recomm. Syst. - RecSys ’11, pp. 133–140, 2011.
[29]F. Ortega, B. Zhu, J. Bobadilla, and A. Hernando, “CF4J: Collaborative filtering for Java,” Knowledge-Based Syst., vol. 152, pp. 94–99, 2018.
[30]D. Goldberg, D. Nichols, B. M. Oki, and D. Terry, “Using collaborative filtering to weave an information tapestry,” Commun. ACM, vol. 35, no. 12, pp. 61–70, 1992.
[31]J. L. Herlocker, J. A. Konstan, A. Borchers, and J. Riedl, “An algorithmic framework for performing collaborative filtering,” in Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR ’99, 1999, pp. 230–237.
[32]J. O. N. Herlocker and J. Riedl, “An Empirical Analysis of Design Choices in Neighborhood-Based Collaborative Filtering Algorithms,” Inf. Retr. Boston., pp. 287–310, 2002.
[33]“Duine Framework - Recommender Software Toolkit.” [Online]. Available: http://www.duineframework.org/. [Accessed: 10-Feb-2019].
[34]“easyrec :: open source recommendation engine.” [Online]. Available: http://easyrec.org/home. [Accessed: 10-Feb-2019].
[35]Y. Koren, R. Bell, and C. Volinsky, “Matrix factorization techniques for recommender systems,” Computer (Long. Beach. Calif)., no. 8, pp. 30–37, 2009.
[36]A. Hernando, J. Bobadilla, and F. Ortega, “A Non-Negative Matrix Factorization for Collaborative Filtering Recommender Systems Based on a Bayesian Probabilistic Model,” Know.-Based Syst., vol. 97, no. C, pp. 188–202, Apr. 2016.
[37]P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl, “GroupLens : An Open Architecture for Collaborative Filtering of Netnews,” in Proceedings of the 1994 ACM conference on Computer supported cooperative work, 1994, pp. 175–186.
[38]J. A. Konstan, B. N. Miller, D. Maltz, J. L. Herlocker, L. R. Gordon, and J. Riedl, “GroupLens: applying collaborative filtering to Usenet news,” Commun. ACM, vol. 40, no. 3, pp. 77–87, 1997.
[39]B. Sarwar, G. Karypis, J. Konstan, and J. Reidl, “Item-based collaborative filtering recommendation algorithms,” Proc. tenth Int. Conf. World Wide Web - WWW ’01, pp. 285–295, 2001.
[40]P. Jaccard, “Distribution comparée de la flore alpine dans quelques régions des Alpes occidentales et orientales,” Bull. la Socit Vaudoise des Sci. Nat., vol. 37, pp. 241–272, 1901.
[41]J. Bobadilla, F. Serradilla, and J. Bernal, “A new collaborative filtering metric that improves the behavior of recommender systems,” Knowledge-Based Syst., vol. 23, no. 6, pp. 520–528, 2010.
[42]J. Bobadilla, F. Ortega, A. Hernando, and Á. Arroyo, “A balanced memory-based collaborative filtering similarity measure,” Int. J. Intell. Syst., vol. 27, no. 10, pp. 939–946, Oct. 2012.
[43]J. Bobadilla, F. Ortega, and A. Hernando, “A collaborative filtering similarity measure based on singularities,” Inf. Process. Manag., vol. 48, no. 2, pp. 204–217, 2012.
[44]H. J. Ahn, “A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem,” Inf. Sci. (Ny)., vol. 178, no. 1, pp. 37–51, 2008.
[45]L. R. Dice, “Measures of the amount of ecologic association between species,” Ecology, vol. 26, no. 3, pp. 297–302, 1945.
[46]M. G. Kendall, “A new measure of rank correlation,” Biometrika, vol. 30, no. 1/2, pp. 81–93, 1938.
[47]T. M. Cover and J. A. Thomas, Elements of information theory, Wiley. Wiley-Interscience, 2006.
[48]J. L. Herlocker, J. A. Konstan, L. G. Terveen, and J. T. Riedl, “Evaluating collaborative filtering recommender systems,” ACM Trans. Inf. Syst., vol. 22, no. 1, pp. 5–53, 2004.
[49] “MovieLens | GroupLens.” [Online]. Available: https://grouplens.org/datasets/movielens/. [Accessed: 22-Dec-2018].
[50]F. M. Harper and J. A. Konstan, “The MovieLens Datasets,” ACM Trans. Interact. Intell. Syst., vol. 5, no. 4, pp. 1–19, 2015.
[51]A. Gunawardana and G. Shani, “A survey of accuracy evaluation metrics of recommendation tasks,” J. Mach. Learn. Res., vol. 10, pp. 2935–2962, 2009.
[52]G. Carenini and R. Sharma, “Exploring More Realistic Evaluation Measures for Collaborative Filtering,” in Proceedings of the 19th National Conference on Artifical Intelligence, 2004, pp. 749–754.
[53]T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature,” Geosci. Model Dev., vol. 7, no. 3, pp. 1247–1250, 2014.