Explainable AI For the Brazilian Stock Market Index: A Post-Hoc Approach to Deep Learning Models in Time-Series Forecasting
Resumo
Time-series forecasting is challenging when data lacks clear trends or seasonality, making traditional statistical models less effective. Deep Learning models, like Neural Networks, excel at capturing non-linear patterns and offer a promising alternative. The Bovespa Index (Ibovespa), a key indicator of Brazil’s stock market, is volatile, leading to potential investor losses due to inaccurate forecasts and limited market insight. Neural Networks can enhance forecast accuracy, but reduce model explainability. This study aims to use Deep Learning to forecast the Ibovespa, striving to balance high forecasting accuracy with model interpretability, to improve decision-making in time-series forecasting and provide valuable insights into the economic landscape of Brazil
Palavras-chave:
xai, time-series, computational inteligence
Referências
A Bolsa do Brasil — B3. B3. [link]. Last accessed on 2024-03-01.
Alain, G. and Bengio, Y. (2016). Understanding intermediate layers using linear classifier probes. arXiv:1610.01644 [stat.ML].
Alkhatib, K., Khazaleh, H., Alkhazaleh, H. A., Alsoud, A. R., and Abualigah, L. (2022). A new stock price forecasting method using active deep learning approach. Journal of Open Innovation: Technology, Market, and Complexity, 8(2):96.
Alzaman, C. (2023). Forecasting and optimization stock predictions: Varying asset profile, time window, and hyperparameter factors. Syst Soft Comput, 5:200052.
Barbosa, B. A., Marcacini, R. M., and Rezende, S. O. (2021). Predição do movimento do índice ibovespa a partir de notícias. In Workshop de Matemática, Estatística e Computação Aplicadas à Indústria - WMECAI. ICMC-USP.
Brazil’s Central Bank. Brazil’s Central Bank Interest Rates. Brazilian Central Bank. [link], last accessed on 2024-02-25.
Bryan-Kinns, N. (2024). Reflections on explainable ai for the arts (xaixarts). Interactions, 31(1):43–47.
Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, page 785–794. ACM.
Choinhet, R., Schmidt, C. E., and Chies, L. (2021). Aplicação da árvore de classificação na predição do movimento do índice ibovespa. Sociedade Brasileira de Automática, 1(1):512–517.
date-holidays JavaScript Library. date-holidays. GitHub, Commenthol. [link], last accessed on 2024-02-25.
de Araujo Morais, L. R. (2024). Forecasting paper xai. Available at: [link], last accessed on 2024-10-01.
Fryer, D., Strümke, I., and Nguyen, H. (2021). Shapley values for feature selection: The good, the bad, and the axioms. IEEE Access, 9:144352–144360.
Hill, T., Marquez, L., O’Connor, M., and Remus, W. (1994). Artificial neural network models for forecasting and decision making. International Journal of Forecasting, 10(1):5–15.
Hyndman, R. J. and Athanasopoulos, G. (2021). Forecasting: Principles and Practice. OTexts, Melbourne, Australia, 3rd edition.
Jat, D. S., Dhaka, P., and Limbo, A. (2018). Applications of statistical techniques and artificial neural networks: A review. Journal of Statistics and Management Systems, 21(4):639–645.
Lim, B., Arık, S. , Loeff, N., and Pfister, T. (2021). Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4):1748–1764.
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Del Ser, J., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., Jiang, R., Khosravi, H., Lecue, F., Malgieri, G., Páez, A., Samek, W., Schneider, J., Speith, T., and Stumpf, S. (2024). Explainable artificial intelligence (xai) 2.0: A manifesto of open challenges and interdisciplinary research directions. Information Fusion, 106:102301.
Martins, T., Almeida, A. M. d., Cardoso, E., and Nunes, L. (2024). Explainable artificial intelligence (xai): A systematic literature review on taxonomies and applications in finance. IEEE Access, 12:618–629.
McKnight, P. E. and Najab, J. (2010). Kruskal-wallis test. In The Corsini Encyclopedia of Psychology, volume 1, pages 1–10. Wiley.
Pamplona, D. and Jorge, C. (2020). An overview of air delay: A case study of the brazilian scenario. Transportation Research Interdisciplinary Perspectives, 7:1–13.
Possatto, A. B. (2022). Painting the black box white: Interpreting an algorithm-based trading strategy. Revista Brasileira de Finanças, 20(3):105–138.
Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). ”why should i trust you?”: Explaining the predictions of any classifier. arXiv:1602.04938 [cs.LG].
Schlegel, U. and Keim, D. A. (2023). A deep dive into perturbations as evaluation technique for time series xai. In Longo, L., editor, Explainable Artificial Intelligence, pages 165–180, Cham. Springer Nature Switzerland.
Shiri, F. M., Perumal, T., Mustapha, N., and Mohamed, R. (2023). A comprehensive overview and comparative analysis on deep learning models: Cnn, rnn, lstm, gru. arXiv:2305.17473.
Siami-Namini, S., Tavakoli, N., and Siami-Namini, A. (2019). A comparative analysis of forecasting financial time series using arima, lstm, and bilstm. arXiv:1911.09512.
Sonkavde, G., Dharrao, D. S., Bongale, A. M., Deokate, S. T., Doreswamy, D., and Bhat, S. K. (2023). Forecasting stock market prices using machine learning and deep learning models: A systematic review, performance analysis and discussion of implications. International Journal of Financial Studies, 11(3):94.
Tabak, B. M. (2006). The dynamic relationship between stock prices and exchange rates: Evidence for brazil. International Journal of Theoretical and Applied Finance, 9(8):1377–1396.
van Zyl, C., Ye, X., and Naidoo, R. (2024). Harnessing explainable artificial intelligence for feature selection in time series energy forecasting: A comparative analysis of grad-cam and shap. Applied Energy, 353:122079.
Yahoo Finance API. Yahoo Finance. yfinance. PyPI, [link], last accessed on 2024-02-25.
Alain, G. and Bengio, Y. (2016). Understanding intermediate layers using linear classifier probes. arXiv:1610.01644 [stat.ML].
Alkhatib, K., Khazaleh, H., Alkhazaleh, H. A., Alsoud, A. R., and Abualigah, L. (2022). A new stock price forecasting method using active deep learning approach. Journal of Open Innovation: Technology, Market, and Complexity, 8(2):96.
Alzaman, C. (2023). Forecasting and optimization stock predictions: Varying asset profile, time window, and hyperparameter factors. Syst Soft Comput, 5:200052.
Barbosa, B. A., Marcacini, R. M., and Rezende, S. O. (2021). Predição do movimento do índice ibovespa a partir de notícias. In Workshop de Matemática, Estatística e Computação Aplicadas à Indústria - WMECAI. ICMC-USP.
Brazil’s Central Bank. Brazil’s Central Bank Interest Rates. Brazilian Central Bank. [link], last accessed on 2024-02-25.
Bryan-Kinns, N. (2024). Reflections on explainable ai for the arts (xaixarts). Interactions, 31(1):43–47.
Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, page 785–794. ACM.
Choinhet, R., Schmidt, C. E., and Chies, L. (2021). Aplicação da árvore de classificação na predição do movimento do índice ibovespa. Sociedade Brasileira de Automática, 1(1):512–517.
date-holidays JavaScript Library. date-holidays. GitHub, Commenthol. [link], last accessed on 2024-02-25.
de Araujo Morais, L. R. (2024). Forecasting paper xai. Available at: [link], last accessed on 2024-10-01.
Fryer, D., Strümke, I., and Nguyen, H. (2021). Shapley values for feature selection: The good, the bad, and the axioms. IEEE Access, 9:144352–144360.
Hill, T., Marquez, L., O’Connor, M., and Remus, W. (1994). Artificial neural network models for forecasting and decision making. International Journal of Forecasting, 10(1):5–15.
Hyndman, R. J. and Athanasopoulos, G. (2021). Forecasting: Principles and Practice. OTexts, Melbourne, Australia, 3rd edition.
Jat, D. S., Dhaka, P., and Limbo, A. (2018). Applications of statistical techniques and artificial neural networks: A review. Journal of Statistics and Management Systems, 21(4):639–645.
Lim, B., Arık, S. , Loeff, N., and Pfister, T. (2021). Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4):1748–1764.
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Del Ser, J., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., Jiang, R., Khosravi, H., Lecue, F., Malgieri, G., Páez, A., Samek, W., Schneider, J., Speith, T., and Stumpf, S. (2024). Explainable artificial intelligence (xai) 2.0: A manifesto of open challenges and interdisciplinary research directions. Information Fusion, 106:102301.
Martins, T., Almeida, A. M. d., Cardoso, E., and Nunes, L. (2024). Explainable artificial intelligence (xai): A systematic literature review on taxonomies and applications in finance. IEEE Access, 12:618–629.
McKnight, P. E. and Najab, J. (2010). Kruskal-wallis test. In The Corsini Encyclopedia of Psychology, volume 1, pages 1–10. Wiley.
Pamplona, D. and Jorge, C. (2020). An overview of air delay: A case study of the brazilian scenario. Transportation Research Interdisciplinary Perspectives, 7:1–13.
Possatto, A. B. (2022). Painting the black box white: Interpreting an algorithm-based trading strategy. Revista Brasileira de Finanças, 20(3):105–138.
Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). ”why should i trust you?”: Explaining the predictions of any classifier. arXiv:1602.04938 [cs.LG].
Schlegel, U. and Keim, D. A. (2023). A deep dive into perturbations as evaluation technique for time series xai. In Longo, L., editor, Explainable Artificial Intelligence, pages 165–180, Cham. Springer Nature Switzerland.
Shiri, F. M., Perumal, T., Mustapha, N., and Mohamed, R. (2023). A comprehensive overview and comparative analysis on deep learning models: Cnn, rnn, lstm, gru. arXiv:2305.17473.
Siami-Namini, S., Tavakoli, N., and Siami-Namini, A. (2019). A comparative analysis of forecasting financial time series using arima, lstm, and bilstm. arXiv:1911.09512.
Sonkavde, G., Dharrao, D. S., Bongale, A. M., Deokate, S. T., Doreswamy, D., and Bhat, S. K. (2023). Forecasting stock market prices using machine learning and deep learning models: A systematic review, performance analysis and discussion of implications. International Journal of Financial Studies, 11(3):94.
Tabak, B. M. (2006). The dynamic relationship between stock prices and exchange rates: Evidence for brazil. International Journal of Theoretical and Applied Finance, 9(8):1377–1396.
van Zyl, C., Ye, X., and Naidoo, R. (2024). Harnessing explainable artificial intelligence for feature selection in time series energy forecasting: A comparative analysis of grad-cam and shap. Applied Energy, 353:122079.
Yahoo Finance API. Yahoo Finance. yfinance. PyPI, [link], last accessed on 2024-02-25.
Publicado
17/11/2024
Como Citar
MORAIS, Lucas Rabelo de Araujo; FRAGOSO, Gabriel Arnaud de Melo; LUDERMIR, Teresa Bernarda; MONTEIRO, Claudio Luis Alves.
Explainable AI For the Brazilian Stock Market Index: A Post-Hoc Approach to Deep Learning Models in Time-Series Forecasting. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 21. , 2024, Belém/PA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 436-447.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2024.244444.
