A Collaborative Filtering Recommender System for Test Case Prioritization in Web Applications

TL;DR

This paper presents a collaborative filtering recommender system that leverages user interaction and change history data to improve test case prioritization in web application regression testing, demonstrating enhanced effectiveness through empirical evaluation.

Contribution

It introduces a novel item-based collaborative filtering approach for test prioritization that integrates user and application data, advancing software testing automation.

Findings

Improved test prioritization effectiveness in web applications.

Recommender system outperforms traditional control techniques.

Effective across multiple application versions.

Abstract

The use of relevant metrics of software systems could improve various software engineering tasks, but identifying relationships among metrics is not simple and can be very time consuming. Recommender systems can help with this decision-making process, many applications have utilized these systems to improve the performance of their applications. To investigate the potential benefits of recommender systems in regression testing, we implemented an item-based collaborative filtering recommender system that uses user interaction data and application change history information to develop a test case prioritization technique. To evaluate our approach, we performed an empirical study using three web applications with multiple versions and compared four control techniques. Our results indicate that our recommender system can help improve the effectiveness of test prioritization.