IJSTR

International Journal of Scientific & Technology Research

IJSTR@Facebook IJSTR@Twitter IJSTR@Linkedin
Home About Us Scope Editorial Board Blog/Latest News Contact Us
Scopus/Elsevier
CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT
QR CODE
IJSTR-QR Code

IJSTR >> Volume 9 - Issue 1, January 2020 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Two Recommendation System Algorithms Used SVD And Association Rule On Implicit And Explicit Data Sets

[Full Text]

 

AUTHOR(S)

Marwa Hussien Mohamed, Mohamed Helmy Khafagy, Mohamed Hasan Ibrahim

 

KEYWORDS

Recommender systems; K-means clustering; Association Rule; SVD (Singular Value Decomposition); Dimensionality Reduction.

 

ABSTRACT

Nowadays, the recommender system is an important research area for online companies that suggest items and services to users like (last FM music, Netflix movies, and movie-lens). Building a recommendation system to meet users' preferences is very difficult due to rapidly increasing the size or volume of digital information. Also, the recommendation has many challenges that need to overcome like sparsity, accuracy, performance and novelty. In this paper, we build two new algorithms to solve the sparsity, accuracy and performance of the recommendation system. Firstly, we used association rule mining to find a hidden pattern and count numbers of played songs per transaction and compute similarities by cosine vector similarity to make a recommendation to users also taking into concern the rating merged with clustering technique. Secondly, we used K-means clustering algorithms with SVD (singular value decomposition) to reduce dimensionality, increase the performance, and solve sparsity and accuracy problems. Our experiments are applied on last FM music datasets and movie-lens datasets implicit and explicit feedback, we compare our new algorithms with k-means collaborative filtering using RMSE (root mean square error) to show the accuracy and performance of movie lens and measure the accuracy using precision, recall and, F- measure to show the accuracy between basic collaborative filtering and our two new algorithms. This experiment shows that using association rule is better than improved k-means while combining with SVD and basic collaborative filtering. But our new k-means and SVD algorithm has better performance than random collaborative filtering K-means.

 

REFERENCES

[1] Sobia Zahra, Mustansar Ali Ghazanfar, Asra Khalid, Muhammad Awais Azam, Usman Naeem, Adam Prugel Bennett, “ Novel centroid selection approaches for KMeans-clustering based recommender systems ”, Information Sciences Vol. 320, pp. 156-189, May 2015.
[2] Shivani Sharma," A Recommender System Based on Improvised K- Means Clustering Algorithm ", International Journal of Research in Advent Technology, Vol.6, No.7, July 2018,pp.1477-1483.
[3] Marwa Hussien Mohamed, Mohamed Helmy Khafagy, Mohamed Hasan Ibrahim . "Recommender Systems Challenges and Solutions Survey", 2019 International Conference on Innovative Trends in Computer Engineering (ITCE’2019), Aswan, Egypt, 2-4 February 2019,pp.149-155
[4] Hamdy Fadl Abdulkarem, Ghada Y. Abozaid, Mostafa I. Soliman"Context-Aware Recommender System Frameworks, Techniques, and Applications: A Survey".2019 International Conference on Innovative Trends in Computer Engineering (ITCE’2019), Aswan, Egypt, 2-4 February 2019,pp.180-185
[5] Gawesh Jawaheer, Martin Szomszor, Patty Kostkova,"Comparison of Implicit and Explicit Feedback from an Online Music Recommendation Service",(2010).doi. 10.1145/1869446.1869453.
[6] Phongsavanh Phorasim,Lasheng Yu." Movies recommendation system using collaborative filtering and k-means", International Journal of Advanced Computer Research, Vol 7(29),pp.52-59.
[7] P. Masethungh, S. Kumaresan," Centroid Selection Approaches for K-Means Clustering based Recommender Systems ",SEEE DIGIBOOK ON ENGINEERING & TECHNOLOGY, VOL. 01, MAY 2018
[8] Lu Yang, Anilkumar Kothalil Gopalakrishnan," A Collaborative Filtering Recommendation Based on User Profile and User Behavior in Online Social Networks", 2014 International Computer Science and Engineering Conference (ICSEC),pp.273-277,2014.
[9] Acilar, A. M, Arslan, A " A collaborative filtering method based on artificial immune network". Expert Systems with Applications 36, (2014),pp. 8324-8332.
[10] Hafed Zarzour, Ziad Al-Sharif, Mahmoud Al-Ayyoub, Yaser Jararweh," A New Collaborative Filtering Recommendation Algorithm Based on Dimensionality Reduction and Clustering Techniques", 9th International Conference on Information and Communication Systems (ICICS) , pp.102-106,2018.
[11] Phongsavanh Phorasim,Lasheng Yu." Movies recommendation system using collaborative filtering and k-means", International Journal of Advanced Computer Research, Vol 7(29),pp.52-59.
[12] http://millionsongdataset.com/lastfm
[13] Gunjan Advani,Neha Soni." A Novel Method for Music Recommendation using Social Media Tags", International Journal of Computer Applications (0975 – 8887) Volume 122 – No.2, July 2015,pp.37-43.
[14] Thierry Bertin-Mahieux, Daniel P.W. Ellis, Brian Whitman, and Paul Lamere."The Million Song Dataset. In Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR 2011), 2011.
[15] F. M. Harper and J. A. Konstan, “The MovieLens Datasets,” ACM Transactions on Interactive Intelligent Systems, vol. 5, no. 4, pp. 1–19,Dec. 2015.
[16] Subhash K. Shinde ⇑, Uday Kulkarni." Hybrid personalized recommender system using centering-bunching based clustering algorithm". Expert Systems with Applications39, 2012, pp. 1381-1387.
[17] Marwa Hussien Mohamed, Mohamed Helmy Khafagy, Mohamed Hasan Ibrahim . “Hash Semi Join Map Reduce to Join Billion Records in a Reasonable Time.” Indian Journal of Science and Technology, vol. 11, no. 18, Jan. 2018, pp. 1–9., doi:10.17485/ijst/2018/v11i18/119112.
[18] Marwa Hussien Mohamed, Mohamed Helmy Khafagy, Mohamed Hasan Ibrahim . "From Two-Way to Multi-Way: A Comparative Study for Map-Reduce Join Algorithms". WSEAS Transactions on Communications, Volume 17, 2018, pp. 129-141.
[19] Marwa Hussien Mohamed and Mohamed Helmy Khafagy. “Hash semi cascade join for joining multi-way map reduce.” 2015 SAI Intelligent Systems Conference (IntelliSys)(2015): pp.355-361.
[20] Li Xie , Wenbo Zhou, Yaosen Li et al. “Application of Improved Recommendation System Based on Spark Platform in Big Data Analysis.” CYBERNETICS AND INFORMATION TECHNOLOGIES, vol. Volume 16, No 6, 2016, pp. 245–55, doi:DOI: 10.1515/cait-2016-0092.
[21] Mostafa rabea Kaseb,Mohamed helmy khafagy,ihab A.Ali,Elsayed M.Saad,"Multi-split HDFS Technique for improving data confidentiality in Big Data Replication",2019 advances in intelligent systems and computing,pp.132-142.
[22] Radya R.sahal,Mohamed helmy khafagy,fatma A.omara,"Big data multi-query optimization with apache flink",international journal of web engineering and technology,2018.
[23] Mostafa rabea Kaseb,Mohamed helmy khafagy,ihab A.Ali,Elsayed M.Saad," Redundent independent files (RIF): A technique for reducing storage and resourses in big data replication ",2018 advances in intelligent systems and computing.