Developing Algorithms for Personalized Recommendations Based on User Behavior
M. Sangeetha, B. Srinivasa Kumar, Kothandapani Chokkanathan, Ashok Kumar, S. Krishna Prabha, Sivakumar Sattanathan, J. K. Periasamy · 2023
To enhance the performance of user personalized recommendation algorithms, this study offers a user personalized recommendation calculation based on deep learning network. Efficient and accurate personalized recommendation algorithms can effectively increase user experience fulfillment. Considering user behavior, this research suggests a useful advice. We offer a preference network that might gather user preferences based on item qualities since customers intuitively convey their considerations based on some specific attributes of items. Moreover, weighted affiliation rules are used to identify these patterns to enhance the nature of recommendations because there are some sequential patterns in item purchases. We offer a preference network that might gather user preferences based on item qualities since customers intuitively convey their contemplations based on some specific attributes of items. Moreover, weighted affiliation rules are used to identify these patterns to enhance the nature of recommendations because there are some sequential patterns in item purchases. The methodology solves the sparsity problem and outperforms existing algorithms. Implementing a user behavior-based recommendation method, which gauges users' interests based on certain evaluations of item qualities, is the primary commitment. Furthermore, this strategy makes use of a sequential purchase pattern to raise the caliber of recommendations.