## Abstract

This chapter introduces the industry context for machine learning in finance, discussing the critical events that have shaped the finance industry’s need for machine learning and the unique barriers to adoption. The finance industry has adopted machine learning to varying degrees of sophistication. How it has been adopted is heavily fragmented by the academic disciplines underpinning the applications. We view some key mathematical examples that demonstrate the nature of machine learning and how it is used in practice, with the focus on building intuition for more technical expositions in later chapters. In particular, we begin to address many finance practitioner’s concerns that neural networks are a “black-box” by showing how they are related to existing well-established techniques such as linear regression, logistic regression, and autoregressive time series models. Such arguments are developed further in later chapters. This chapter also introduces reinforcement learning for finance and is followed by more in-depth case studies highlighting the design concepts and practical challenges of applying machine learning in practice.

## References

- Akaike, H. (1973).
*Information theory and an extension of the maximum likelihood principle*(pp. 267–281).Google Scholar - Akcora, C. G., Dixon, M. F., Gel, Y. R., & Kantarcioglu, M. (2018). Bitcoin risk modeling with blockchain graphs.
*Economics Letters,**173*(C), 138–142.zbMATHGoogle Scholar - Arnold, V. I. (1957).
*On functions of three variables*(Vol. 114, pp. 679–681).Google Scholar - Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity.
*Journal of Econometrics,**31*, 307–327.MathSciNetzbMATHGoogle Scholar - Box, G. E. P., & Jenkins, G. M. (1976).
*Time series analysis, forecasting, and control*. San Francisco: Holden-Day.zbMATHGoogle Scholar - Box, G. E. P., Jenkins, G. M., & Reinsel, G. C. (1994).
*Time series analysis, forecasting, and control*(third ed.). Englewood Cliffs, NJ: Prentice-Hall.zbMATHGoogle Scholar - Breiman, L. (2001). Statistical modeling: the two cultures (with comments and a rejoinder by the author).
*Statistical Science,**16*(3), 199–231.MathSciNetzbMATHGoogle Scholar - Cont, R., & de Larrard, A. (2013). Price dynamics in a Markovian limit order market.
*SIAM Journal on Financial Mathematics,**4*(1), 1–25.MathSciNetzbMATHGoogle Scholar - de Prado, M. (2018).
*Advances in financial machine learning*. Wiley.Google Scholar - de Prado, M. L. (2019). Beyond econometrics: A roadmap towards financial machine learning.
*SSRN*. Available at SSRN: https://ssrn.com/abstract=3365282 or http://dx.doi.org/10.2139/ssrn.3365282. - DeepMind (2016). DeepMind AI reduces Google data centre cooling bill by 40%. https://deepmind.com/blog/deepmind-ai-reduces-google-data-centre-cooling-bill-40/.
- DeepMind (2017). The story of AlphaGo so far. https://deepmind.com/research/alphago/.
- Dixon, M. (2018a). A high frequency trade execution model for supervised learning.
*High Frequency,**1*(1), 32–52.Google Scholar - Dixon, M. (2018b). Sequence classification of the limit order book using recurrent neural networks.
*Journal of Computational Science,**24*, 277–286.MathSciNetGoogle Scholar - Dixon, M., & Halperin, I. (2019).
*The four horsemen of machine learning in finance*.Google Scholar - Dixon, M., Polson, N., & Sokolov, V. (2018). Deep learning for spatio-temporal modeling: Dynamic traffic flows and high frequency trading.
*ASMB*.Google Scholar - Dixon, M. F., & Polson, N. G. (2019, Mar). Deep fundamental factor models.
*arXiv e-prints*, arXiv:1903.07677.Google Scholar - Dyhrberg, A. (2016). Bitcoin, gold and the dollar – a GARCH volatility analysis.
*Finance Research Letters*.Google Scholar - Elman, J. L. (1991, Sep). Distributed representations, simple recurrent networks, and grammatical structure.
*Machine Learning,**7*(2), 195–225.Google Scholar - Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks.
*Nature,**542*(7639), 115–118.Google Scholar - Flood, M., Jagadish, H. V., & Raschid, L. (2016). Big data challenges and opportunities in financial stability monitoring.
*Financial Stability Review,*(20), 129–142.Google Scholar - Gomber, P., Koch, J.-A., & Siering, M. (2017). Digital finance and fintech: current research and future research directions.
*Journal of Business Economics,**7*(5), 537–580.Google Scholar - Gottlieb, O., Salisbury, C., Shek, H., & Vaidyanathan, V. (2006). Detecting corporate fraud: An application of machine learning. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.7470.Google Scholar
- Graves, A. (2012).
*Supervised sequence labelling with recurrent neural networks*. Studies in Computational intelligence. Heidelberg, New York: Springer.Google Scholar - Gu, S., Kelly, B. T., & Xiu, D. (2018).
*Empirical asset pricing via machine learning*. Chicago Booth Research Paper 18–04.Google Scholar - Harvey, C. R., Liu, Y., & Zhu, H. (2016). …and the cross-section of expected returns.
*The Review of Financial Studies,**29*(1), 5–68.Google Scholar - Hornik, K., Stinchcombe, M., & White, H. (1989, July). Multilayer feedforward networks are universal approximators.
*Neural Netw.,**2*(5), 359–366.zbMATHGoogle Scholar - Kearns, M., & Nevmyvaka, Y. (2013). Machine learning for market microstructure and high frequency trading.
*High Frequency Trading - New Realities for Traders*.Google Scholar - Kercheval, A., & Zhang, Y. (2015). Modeling high-frequency limit order book dynamics with support vector machines.
*Journal of Quantitative Finance,**15*(8), 1315–1329.zbMATHGoogle Scholar - Kolmogorov, A. N. (1957). On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition.
*Dokl. Akad. Nauk SSSR,**114*, 953–956.MathSciNetzbMATHGoogle Scholar - Kubota, T. (2017, January). Artificial intelligence used to identify skin cancer.Google Scholar
- Kullback, S., & Leibler, R. A. (1951, 03). On information and sufficiency.
*Ann. Math. Statist.,**22*(1), 79–86.zbMATHGoogle Scholar - McCarthy, J., Minsky, M. L., Rochester, N., & Shannon, C. E. (1955, August). A proposal for the Dartmouth summer research project on artificial intelligence. http://www-formal.stanford.edu/jmc/history/dartmouth/dartmouth.html.
- Philipp, G., & Carbonell, J. G. (2017, Dec). Nonparametric neural networks.
*arXiv e-prints*, arXiv:1712.05440.Google Scholar - Philippon, T. (2016).
*The fintech opportunity*. CEPR Discussion Papers 11409, C.E.P.R. Discussion Papers.Google Scholar - Pinar Saygin, A., Cicekli, I., & Akman, V. (2000, November). Turing test: 50 years later.
*Minds Mach.,**10*(4), 463–518.Google Scholar - Poggio, T. (2016). Deep learning: mathematics and neuroscience.
*A Sponsored Supplement to Science**Brain-Inspired intelligent robotics: The intersection of robotics and neuroscience*, 9–12.Google Scholar - Shannon, C. (1948). A mathematical theory of communication.
*Bell System Technical Journal,**27*.Google Scholar - Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition.Google Scholar
- Sirignano, J., Sadhwani, A., & Giesecke, K. (2016, July). Deep learning for mortgage risk.
*ArXiv e-prints*.Google Scholar - Sirignano, J. A. (2016). Deep learning for limit order books.
*arXiv preprint arXiv:1601.01987*.Google Scholar - Sovbetov, Y. (2018). Factors influencing cryptocurrency prices: Evidence from Bitcoin, Ethereum, Dash, Litcoin, and Monero.
*Journal of Economics and Financial Analysis,**2*(2), 1–27.Google Scholar - Stein, H. (2012). Counterparty risk, CVA, and Basel III.Google Scholar
- Turing, A. M. (1995).
*Computers & thought*. Chapter Computing Machinery and Intelligence (pp. 11–35). Cambridge, MA, USA: MIT Press.Google Scholar - Wiener, N. (1964).
*Extrapolation, interpolation, and smoothing of stationary time series*. The MIT Press.Google Scholar