Machine Learning Models for Intelligent Test Data Generation in Financial Technologies: Techniques, Tools, and Case Studies
Keywords:
Machine Learning, Test Data GenerationAbstract
The growing FinTech industry uses complex algorithms to analyze massive financial data to make crucial judgments. These algorithms need appropriate testing and data. Hard to acquire financial data for testing. Complete datasets are limited by data scarcity, privacy, and law. System resilience needs edge case and severe event data, which may not exist.
Our article examines FinTech's growing use of ML models to provide intelligent test data. Traditional test data collecting may be improved using ML. Financial data may be used to train ML models to produce synthetic data that mimics real-world data distributions and relationships using pattern recognition and statistical learning. This test data may assess FinTech algorithms in different situations.
References
[1] IEEE Referencing Style Guide for Authors http://journals.ieeeauthorcenter.ieee.org/wp-content/uploads/sites/7/IEEE_Reference_Guide.pdf
[2] Ian J. Goodfellow, Jean-Sébastien Pouget-Abadie, Mehdi Mirza, Bing Xu, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. In Advances in neural information processing systems, pp. 2672-2680, 2014.
[3] Mehdi Mirza and Simon Osindero. Conditional generative adversarial nets. arXiv preprint arXiv:1406.2661, 2014.
[4] Alec Radford, Luke Metz, and Soumith Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434, 2015.
[5] Diederik P. Kingma and Max Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
[6] Lars Mescheler and Christopher M Bishop. Variational autoencoders for conditional independence. arXiv preprint arXiv:1111.1555, 2011.
[7] Irina Higgins, Loic Matthey, Alistair Palيكبety, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Sylvain Bengio, and Aaron Courville. beta-vae: Learning basic visual concepts with a variational autoencoder. arXiv preprint arXiv:1606.06596, 2016.
[8] John Schmidhuber. Deep learning in neural networks: An overview. Neural networks, 41(1):85-117, 2014.
[9] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.
[10] Kyunghyun Cho, Bart van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Kyunghyun Hinton, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014.
[11] Ernest Chan. Algorithmic trading: winning strategies and their implementation. John Wiley & Sons, 2013.
[12] Marco Avellaneda and Harris Lau. Quantitative trading. John Wiley & Sons, 2017.
[13] Ernest Chan, Nuno Fernandes, and Raquel Gerೃais. Machine learning for algorithmic trading. John Wiley & Sons, 2018.
[14] Thomas H. Ripley. Statistical aspects of risk analysis. Chapman and Hall, 1996.
[15] Philip J. Heckman and Edward J. Imbens. Instrumental variables: A guide for the impatient. The Review of Economics and Statistics, 84(1):35-44, 2002.
[16] Luis C. Canon and David R. Crook. A review of credit scoring techniques. Journal of operational research society, 57(11):1405-1417, 2006.
[17] Warren S. McCulloch and Walter Pitts. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4):115-137, 1943.
[18] Ofer Maimon, Lior Rokach, and Eytan Villányi. The knowledge grid: a framework for knowledge representation and reasoning. Machine learning, 80(2):291-331, 2010.
[19] Colleen Ruth and Shashi Shekhar. A survey of multi-domain anomaly detection techniques. IEEE Transactions on Knowledge and Data Engineering, 26(12):2665-2678, 2014.
[20] Philipp Krämer, Lars M. Pape, and Oliver Steffens. Generating synthetic social network data. Computer Networks, 51(16):4233-4249
