Learning data characteristics of a session-based recommendation system and their impact on system performance

Authors

  • Urszula Kużelewska Faculty of Computer Science, Bialystok Universityof Technology, Bialystok, Poland

DOI:

https://doi.org/10.24425/ijet.2025.153579

Abstract

Recommendation systems are the most effective solution for enhancing user satisfaction and personalising ecommerce services on the internet. These systems use advanced procedures to analyse massive volumes of data, ensuring users receive the most relevant and suitable products available. The success of recommendation systems hinges on the quality of the methods used. However, there is also an impact on the input data. Session-based techniques are the most effective way to generate recommendations. They focus on short-term user interactions organised in sessions. This procedure is the best for real-world scenarios, where one-time users and limited item availability are prevalent. The objective of this study is to examine the relationship between data metrics, including density, shape, and popularity, and the performance of session-based algorithms, in terms of accuracy and coverage.

Published

2025-01-07

How to Cite

Kużelewska, Urszula. “Learning Data Characteristics of a Session-Based Recommendation System and Their Impact on System Performance”. International Journal of Electronics and Telecommunications, vol. 71, no. 2, Jan. 2025, doi:10.24425/ijet.2025.153579.

Issue

Section

Artykuły