Skip to main content
Top

Hint

Swipe to navigate through the chapters of this book

2021 | OriginalPaper | Chapter

Explainable AI (XAI) Models Applied to the Multi-agent Environment of Financial Markets

Authors : Jean Jacques Ohana, Steve Ohana, Eric Benhamou, David Saltiel, Beatrice Guez

Published in: Explainable and Transparent AI and Multi-Agent Systems

Publisher: Springer International Publishing

share
SHARE

Abstract

Financial markets are a real life multi-agent system that is well known to be hard to explain and interpret. We consider a gradient boosting decision trees (GBDT) approach to predict large S&P 500 price drops from a set of 150 technical, fundamental and macroeconomic features. We report an improved accuracy of GBDT over other machine learning (ML) methods on the S&P 500 futures prices. We show that retaining fewer and carefully selected features provides improvements across all ML approaches. Shapley values have recently been introduced from game theory to the field of ML. They allow for a robust identification of the most important variables predicting stock market crises, and of a local explanation of the crisis probability at each date, through a consistent features attribution. We apply this methodology to analyse in detail the March 2020 financial meltdown, for which the model offered a timely out of sample prediction. This analysis unveils in particular the contrarian predictive role of the tech equity sector before and after the crash.
Literature
1.
go back to reference Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018) CrossRef Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018) CrossRef
2.
go back to reference Aguilar-Rivera, R., Valenzuela-Rendón, M., Rodríguez-Ortiz, J.: Genetic algorithms and Darwinian approaches in financial applications: a survey. Expert Syst. Appl. 42(21), 7684–7697 (2015) CrossRef Aguilar-Rivera, R., Valenzuela-Rendón, M., Rodríguez-Ortiz, J.: Genetic algorithms and Darwinian approaches in financial applications: a survey. Expert Syst. Appl. 42(21), 7684–7697 (2015) CrossRef
3.
go back to reference Atsalakis, G.S., Valavanis, K.P.: Surveying stock market forecasting techniques - part II: soft computing methods. Expert Syst. Appl. 36(3, Part 2), 5932–5941 (2009) CrossRef Atsalakis, G.S., Valavanis, K.P.: Surveying stock market forecasting techniques - part II: soft computing methods. Expert Syst. Appl. 36(3, Part 2), 5932–5941 (2009) CrossRef
4.
go back to reference Benhamou, E.: Connecting Sharpe ratio and Student t-statistic, and beyond. ArXiv (2019) Benhamou, E.: Connecting Sharpe ratio and Student t-statistic, and beyond. ArXiv (2019)
5.
go back to reference Benhamou, E., Guez, B.: Incremental Sharpe and other performance ratios. J. Stat. Econom. Methods 2018 (2018) Benhamou, E., Guez, B.: Incremental Sharpe and other performance ratios. J. Stat. Econom. Methods 2018 (2018)
6.
go back to reference Benhamou, E., Guez, B., Paris, N.: Omega and Sharpe ratio. ArXiv (2019) Benhamou, E., Guez, B., Paris, N.: Omega and Sharpe ratio. ArXiv (2019)
7.
go back to reference Benhamou, E., Saltiel, D., Guez, B., Paris, N.: Testing Sharpe ratio: luck or skill? ArXiv (2019) Benhamou, E., Saltiel, D., Guez, B., Paris, N.: Testing Sharpe ratio: luck or skill? ArXiv (2019)
8.
go back to reference Benhamou, E., Saltiel, D., Ohana, J.J., Atif, J.: Detecting and adapting to crisis pattern with context based deep reinforcement learning. In: International Conference on Pattern Recognition (ICPR). IEEE Computer Society (2021) Benhamou, E., Saltiel, D., Ohana, J.J., Atif, J.: Detecting and adapting to crisis pattern with context based deep reinforcement learning. In: International Conference on Pattern Recognition (ICPR). IEEE Computer Society (2021)
10.
go back to reference Benhamou, E., Saltiel, D., Ungari, S., Mukhopadhyay, A.: Bridging the gap between Markowitz planning and deep reinforcement learning. In: Proceedings of the 30th International Conference on Automated Planning and Scheduling (ICAPS): PRL. AAAI Press (2020) Benhamou, E., Saltiel, D., Ungari, S., Mukhopadhyay, A.: Bridging the gap between Markowitz planning and deep reinforcement learning. In: Proceedings of the 30th International Conference on Automated Planning and Scheduling (ICAPS): PRL. AAAI Press (2020)
11.
go back to reference Benhamou, E., Saltiel, D., Ungari, S., Mukhopadhyay, A.: Time your hedge with deep reinforcement learning. In: Proceedings of the 30th International Conference on Automated Planning and Scheduling (ICAPS): FinPlan. AAAI Press (2020) Benhamou, E., Saltiel, D., Ungari, S., Mukhopadhyay, A.: Time your hedge with deep reinforcement learning. In: Proceedings of the 30th International Conference on Automated Planning and Scheduling (ICAPS): FinPlan. AAAI Press (2020)
12.
go back to reference Benhamou, E., Saltiel, D., Vérel, S., Teytaud, F.: BCMA-ES: a Bayesian approach to CMA-ES. CoRR abs/1904.01401 (2019) Benhamou, E., Saltiel, D., Vérel, S., Teytaud, F.: BCMA-ES: a Bayesian approach to CMA-ES. CoRR abs/1904.01401 (2019)
13.
go back to reference Brown, I., Mues, C.: An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert Syst. Appl. 39(3), 3446–3453 (2012) CrossRef Brown, I., Mues, C.: An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert Syst. Appl. 39(3), 3446–3453 (2012) CrossRef
14.
go back to reference Chatzis, S., Siakoulis, A.P.V., Stavroulakis, E., Vlachogiannakis, N.: Forecasting stock market crisis events using deep and statistical machine learning techniques. Expert Syst. Appl. 112, 353–371 (2018) CrossRef Chatzis, S., Siakoulis, A.P.V., Stavroulakis, E., Vlachogiannakis, N.: Forecasting stock market crisis events using deep and statistical machine learning techniques. Expert Syst. Appl. 112, 353–371 (2018) CrossRef
15.
go back to reference Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. CoRR abs/1603.02754 (2016) Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. CoRR abs/1603.02754 (2016)
16.
go back to reference Choo, J., Liu, S.: Visual analytics for explainable deep learning. CoRR abs/1804.02527 (2018) Choo, J., Liu, S.: Visual analytics for explainable deep learning. CoRR abs/1804.02527 (2018)
17.
go back to reference Ghosal, S., Blystone, D., Singh, A.K., Ganapathysubramanian, B., Singh, A., Sarkar, S.: An explainable deep machine vision framework for plant stress phenotyping. Proc. Natl. Acad. Sci. 115(18), 4613–4618 (2018) CrossRef Ghosal, S., Blystone, D., Singh, A.K., Ganapathysubramanian, B., Singh, A., Sarkar, S.: An explainable deep machine vision framework for plant stress phenotyping. Proc. Natl. Acad. Sci. 115(18), 4613–4618 (2018) CrossRef
18.
go back to reference Gu, S., Kelly, B., Xiu, D.: Empirical asset pricing via machine learning. Rev. Financ. Stud. 33(5), 2223–2273 (2020) CrossRef Gu, S., Kelly, B., Xiu, D.: Empirical asset pricing via machine learning. Rev. Financ. Stud. 33(5), 2223–2273 (2020) CrossRef
19.
go back to reference Ke, G., et al.: LightGBM: a highly efficient gradient boosting decision tree. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 3146–3154. Curran Associates, Inc. (2017) Ke, G., et al.: LightGBM: a highly efficient gradient boosting decision tree. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 3146–3154. Curran Associates, Inc. (2017)
20.
go back to reference Kingma, D., Ba, J.: Adam: a method for stochastic optimization (2014) Kingma, D., Ba, J.: Adam: a method for stochastic optimization (2014)
21.
go back to reference Krauss, C., Do, X.A., Huck, N.: Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the S&P 500. Eur. J. Oper. Res. 259(2), 689–702 (2017) CrossRef Krauss, C., Do, X.A., Huck, N.: Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the S&P 500. Eur. J. Oper. Res. 259(2), 689–702 (2017) CrossRef
22.
go back to reference Li, Y., Ma, W.: Applications of artificial neural networks in financial economics: a survey. In: 2010 International Symposium on Computational Intelligence and Design, vol. 1, pp. 211–214 (2010) Li, Y., Ma, W.: Applications of artificial neural networks in financial economics: a survey. In: 2010 International Symposium on Computational Intelligence and Design, vol. 1, pp. 211–214 (2010)
23.
go back to reference Liu, S., Wang, X., Liu, M., Zhu, J.: Towards better analysis of machine learning models: a visual analytics perspective. CoRR abs/1702.01226 (2017) Liu, S., Wang, X., Liu, M., Zhu, J.: Towards better analysis of machine learning models: a visual analytics perspective. CoRR abs/1702.01226 (2017)
24.
go back to reference Lundberg, S., Lee, S.I.: A unified approach to interpreting model predictions (2017) Lundberg, S., Lee, S.I.: A unified approach to interpreting model predictions (2017)
26.
go back to reference Malhi, A., Kampik, T., Pannu, H.S., Madhikermi, M., Främling, K.: Explaining machine learning-based classifications of in-vivo gastral images. In: 2019 Digital Image Computing: Techniques and Applications (DICTA), p. 7, December 2019 Malhi, A., Kampik, T., Pannu, H.S., Madhikermi, M., Främling, K.: Explaining machine learning-based classifications of in-vivo gastral images. In: 2019 Digital Image Computing: Techniques and Applications (DICTA), p. 7, December 2019
28.
go back to reference Marceau, L., Qiu, L., Vandewiele, N., Charton, E.: A comparison of deep learning performances with others machine learning algorithms on credit scoring unbalanced data. CoRR abs/1907.12363 (2019) Marceau, L., Qiu, L., Vandewiele, N., Charton, E.: A comparison of deep learning performances with others machine learning algorithms on credit scoring unbalanced data. CoRR abs/1907.12363 (2019)
29.
go back to reference Mehra, R., Prescott, E.: The equity premium: a puzzle. J. Monet. Econ. 15(2), 145–161 (1985) CrossRef Mehra, R., Prescott, E.: The equity premium: a puzzle. J. Monet. Econ. 15(2), 145–161 (1985) CrossRef
31.
go back to reference Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., Gulin, A.: CatBoost: unbiased boosting with categorical features. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 6638–6648. Curran Associates, Inc. (2018) Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., Gulin, A.: CatBoost: unbiased boosting with categorical features. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 6638–6648. Curran Associates, Inc. (2018)
32.
go back to reference Ribeiro, M.T., Singh, S., Guestrin, C.: “why should i trust you?”: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144. Association for Computing Machinery (2016) Ribeiro, M.T., Singh, S., Guestrin, C.: “why should i trust you?”: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144. Association for Computing Machinery (2016)
33.
go back to reference Rosenfeld, A., Richardson, A.: Explainability in human-agent systems. CoRR abs/1904.08123 (2019) Rosenfeld, A., Richardson, A.: Explainability in human-agent systems. CoRR abs/1904.08123 (2019)
34.
go back to reference Rundo, F., Trenta, F., di Stallo, A.L., Battiato, S.: Machine learning for quantitative finance applications: a survey. Appl. Sci. 9(24), 5574 (2019) CrossRef Rundo, F., Trenta, F., di Stallo, A.L., Battiato, S.: Machine learning for quantitative finance applications: a survey. Appl. Sci. 9(24), 5574 (2019) CrossRef
35.
go back to reference Samitas, A., Kampouris, E., Kenourgios, D.: Machine learning as an early warning system to predict financial crisis. Int. Rev. Financ. Anal. 71, 101507 (2020) CrossRef Samitas, A., Kampouris, E., Kenourgios, D.: Machine learning as an early warning system to predict financial crisis. Int. Rev. Financ. Anal. 71, 101507 (2020) CrossRef
36.
go back to reference Sezer, O.B., Gudelek, M.U., Ozbayoglu, A.M.: Financial time series forecasting with deep learning: a systematic literature review: 2005–2019. arXiv preprint arXiv:​1911.​13288 (2019) Sezer, O.B., Gudelek, M.U., Ozbayoglu, A.M.: Financial time series forecasting with deep learning: a systematic literature review: 2005–2019. arXiv preprint arXiv:​1911.​13288 (2019)
37.
go back to reference Shah, D., Isah, H., Zulkernine, F.: Stock market analysis: a review and taxonomy of prediction techniques. Int. J. Financ. Stud. 7(2), 26 (2019) CrossRef Shah, D., Isah, H., Zulkernine, F.: Stock market analysis: a review and taxonomy of prediction techniques. Int. J. Financ. Stud. 7(2), 26 (2019) CrossRef
38.
go back to reference Sornette, D., Johansen, A.: Significance of log-periodic precursors to financial crashes. Quant. Finance 1, 452–471 (2001) CrossRef Sornette, D., Johansen, A.: Significance of log-periodic precursors to financial crashes. Quant. Finance 1, 452–471 (2001) CrossRef
Metadata
Title
Explainable AI (XAI) Models Applied to the Multi-agent Environment of Financial Markets
Authors
Jean Jacques Ohana
Steve Ohana
Eric Benhamou
David Saltiel
Beatrice Guez
Copyright Year
2021
DOI
https://doi.org/10.1007/978-3-030-82017-6_12

Premium Partner