Generating Test Data Using Generative AI

Master Thesis for the master study programs offered by the Departament of Informatics, Faculty of Natural Sciences, University of Tirana.

Abstract:

This thesis aims to explore the use of generative AI for automated test data generation. Students will investigate different AI models to generate diverse and realistic test datasets, analyze their effectiveness in improving test coverage, and assess their integration into testing frameworks.

The study will involve designing experiments to evaluate AI-generated test data and comparing it with traditional methods. The findings will contribute to understanding the potential of generative AI in software testing and provide insights into its practical applications.

Starting Point:

Baudry, B., Etemadi, K., Fang, S., Gamage, Y., Liu, Y., Liu, Y., … & Tiwari, D. (2024). Generative AI to Generate Test Data Generators. arXiv preprint arXiv:2401.17626.

Goyal, M., & Mahmoud, Q. H. (2024). A systematic review of synthetic data generation techniques using generative AI. Electronics, 13(17), 3509.

Mock, M., Melegati, J., & Russo, B. (2024, June). Generative AI for Test Driven Development: Preliminary Results. In International Conference on Agile Software Development (pp. 24-32). Cham: Springer Nature Switzerland.