Effective time context based collaborative filtering recommender system inspired by Gowers coefficient

Title

Effective time context based collaborative filtering recommender system inspired by Gowers coefficient

Creator

Jain G.; Mahara T.; C.Sharma S.

Description

The fast growth of Internet technology in recent times has led to a surge in the number of users and amount of information generated. This substantially contributes to the popularity of recommendation systems (RS), which provides personalized recommendations to users based on their interests. A RS assists the user in the decision-making process by suggesting a suitable product from various alternatives. The collaborative filtering (CF) technique of RS is the most prevalent because of its high accuracy in predicting users' interests. The efficacy of this technique mainly depends on the similarity calculation, determined by a similarity measure. However, the traditional and previously developed similarity measures in CF techniques are not able to adequately reveal the change in users' interests; therefore, an efficient measure considering time into context is proposed in this paper. The proposed method and the existing approaches are compared on the MovieLens-100k dataset, showing that the proposed method is more efficient than the comparable methods. Besides this, most of the CF approaches only focus on the historical preference of the users, but in real life, the people's preferences also change over time. Therefore, a time-based recommendation system using the proposed method is also developed in this paper. We implemented various time decay functions, i.e., exponential, convex, linear, power, etc., at various levels of the recommendation process, i.e., similarity computation, rating matrix, and prediction level. Experimental results over three real datasets (MovieLens-100k, Epinions, and Amazon Magazine Subscription) suggest that the power decay function outperforms other existing techniques when applied at the rating matrix level. 2022, The Author(s) under exclusive licence to The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and The Division of Operation and Maintenance, Lulea University of Technology, Sweden.

Source

International Journal of System Assurance Engineering and Management, Vol-14, No. 1, pp. 429-447.

Date

2023-01-01

Publisher

Springer

Subject

Collaborative filtering; Gowers coefficient; Recommendation system; Similarity measure; Time decay function

Coverage

Jain G., Indian Institute of Technology Roorkee, Uttarakhand, Roorkee, 247667, India; Mahara T., Christ University, Bengaluru, India; C.Sharma S., Indian Institute of Technology Roorkee, Uttarakhand, Roorkee, 247667, India

Rights

Restricted Access

Relation

ISSN: 9756809

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.1007/s13198-022-01813-z

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85144850040&doi=10.1007%2fs13198-022-01813-z&partnerID=40&md5=24795dd2329899fa8303fa706da18ef8