AI-Driven Approaches for Test Data Generation in FinTech Applications: Enhancing Software Quality and Reliability
Keywords:
FinTech applications, AI-driven testingAbstract
FinTech has risen significantly thanks to mobile and internet banking. Safe software is needed for advanced FinTech applications that handle financial data. FinTech advances are too quick for manual or semi-automated test data creation. Reduced test coverage may reveal weaknesses and damage money or reputation. AI-driven test data production in FinTech apps may alter, says study. AI can automate realistic and diverse test data generation using machine learning and new methodologies, boosting software testing.
Research examines AI-generated test data. Popular generating models include GANs and VAEs. The financial data may teach computers patterns and relationships. Synthetic test data may contain real transactions, edge situations, and anomalies. Testing finds flaws and ensures FinTech application resiliency in different conditions. Other methods include reinforcement learning. The FinTech app's AI bot tests features and edge scenarios. This approach may uncover unexpected user or system behavior to find major bugs that traditional testing overlooks.
References
Yoo, S., & Harman, M. (2012, September). Regression testing using search based test data generation. In 2012 IEEE Fifth International Conference on Software Testing, Verification and Validation (ICST) (pp. 135-144). IEEE. [DOI: 10.1109/ICST.2012.6417122]
Xu, W., & Chandra, S. (2017, July). A survey of automated software testing. ACM Computing Surveys (CSUR), 50(4), 1-43. [DOI: 10.1145/3098910]
Mao, Z., Liu, Y., Xie, X., Li, J., Zhao, J., Sun, Y., & Liu, Z. (2019). Deepmutation: Integrating deep learning with mutation testing for bug detection. In Proceedings of the 2019 27th ACM SIGSOFT International Symposium on Software Testing and Analysis (pp. 87-98). [DOI: 10.1145/3324225.3324252]
Harman, M., & Jones, B. F. (2001, August). Search based software engineering for testing and analysis. Software Testing, Verification and Reliability, 11(4), 293-321. [DOI: 10.1002/stv.436]
Chen, T. Y., Cheung, S. C., Mak, S. W., & Lin, Y. S. (2018, November). Deep learning for internet of things: A survey. Journal of Network and Computer Applications, 110, 328-350. [DOI: 10.1016/j.jnca.2018.01.010]
Wang, W., Zeng, G., Guo, H., Cheng, X., & Liu, J. (2019, June). A survey on the application of deep learning in financial big data. Artificial Intelligence Review, 52(2), 567-608. [DOI: 10.1007/s10472-017-9621-8]
Zheng, Z., Zhao, J., Li, Y., Tian, Y., & Luo, Z. (2020, September). Applications of machine learning in financial risk management: A literature review. Journal of Risk and Financial Management, 13(9), 171. [DOI: 10.3390/jrfm13090171]
Gai, K., Zhu, L., & Liao, X. (2019, April). A survey on privacy-preserving deep learning for financial data analysis. IEEE Access, 7, 62213-62228. [DOI: 10.1109/ACCESS.2019.2918948]
Wu, D., Ding, W., Lin, W., & Zhu, X. (2019, January). Deep learning for financial time series forecasting: A survey. Journal of the American Statistical Association, 114(527), 1-27. [DOI: 10.1080/01621459.2017.1418172]
Panchal, R., Chen, S., & Wu, Y. (2020, March). Artificial intelligence (AI) for detecting fraudulent activities in financial transactions: A survey. Knowledge-Based Systems, 187, 104001. [DOI: 10.1016/j.knosys.2019.104001]
Li, S., Zhu, L., & Huang, X. (2019, April). Survey of data security and privacy in cloud computing. IEEE Access, 7, 70071-70091. [DOI: 10.1109/ACCESS.2019.2912002]
