TD?DNN: A Time Decay?Based Deep Neural Network for Recommendation System

Title

TD?DNN: A Time Decay?Based Deep Neural Network for Recommendation System

Creator

Jain G.; Mahara T.; Sharma S.C.; Agarwal S.; Kim H.

Description

In recent years, commercial platforms have embraced recommendation algorithms to provide customers with personalized recommendations. Collaborative Filtering is the most widely used technique of recommendation systems, whose accuracy is primarily reliant on the computed similarity by a similarity measure. Data sparsity is one problem that affects the performance of the similarity measures. In addition, most recommendation algorithms do not remove noisy data from datasets while recommending the items, reducing the accuracy of the recommendation. Further-more, existing recommendation algorithms only consider historical ratings when recommending the items to users, but users tastes may change over time. To address these issues, this research presents a Deep Neural Network based on Time Decay (TD?DNN). In the data preprocessing phase of the model, noisy ratings are detected from the dataset and corrected using the Matrix Factorization approach. A power decay function is applied to the preprocessed input to provide more weight-age to the recent ratings. This non?noisy weighted matrix is fed into the Deep Learning model, con-sisting of an input layer, a Multi?Layer Perceptron, and an output layer to generate predicted rat-ings. The models performance is tested on three benchmark datasets, and experimental results con-firm that TD?DNN outperforms other existing approaches. 2022 by the authors. Li-censee MDPI, Basel, Switzerland.

Source

Applied Sciences (Switzerland), Vol-12, No. 13

Date

2022-01-01

Publisher

MDPI

Subject

Collaborative Filtering; Deep Neural Network; Matrix Factorization; noisy ratings; recommendation system; time decay functions

Coverage

Jain G., Electronics and Computer Discipline, Indian Institute of Technology, Roorkee, 247667, India; Mahara T., Institute of Management, Christ University, Bengaluru, 560029, India; Sharma S.C., Electronics and Computer Discipline, Indian Institute of Technology, Roorkee, 247667, India; Agarwal S., Amity School of Engineering & Technology, Amity University Uttar Pradesh, Noida, 201313, India; Kim H., School of Computer Science, Kyungil University, Kyungbuk, Gyeongsan, 38428, South Korea

Rights

All Open Access; Gold Open Access

Relation

ISSN: 20763417

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.3390/app12136398

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85132983140&doi=10.3390%2fapp12136398&partnerID=40&md5=db330081d3f470cf8ade841ecf8e6576