Forecasting the Direction of Brazilian Stock Prices Using Neural Networks and Support Vector Machines

• Carlos A. M. Monteiro IFC
• Matheus H. D. M. Ribeiro UTFPR

DOI: https://doi.org/10.5753/encompif.2024.1983

Abstract

The efficient market hypothesis classifies markets as efficient, in which it is not possible to predict the future price, and less efficient, in which it is possible to predict the future price. Considering the possible financial gain when predicting the future price of an asset, several studies use Artificial Intelligence techniques to predict movements in the stock market. This article aims to evaluate the effectiveness of Support Vector Machine and Neural Networks models to predict the behavior of Brazilian stocks, using technical indicators. The results indicate accuracies close to 50% for both models, suggesting that the market is efficient and questioning its forecasting capacity.

References

CHANG, C. LIN, C. LIBSVM: A Library for Support Vector Machines. 2022.

DASH, R.; DASH, P. K. A hybrid stock trading framework integrating technical analysis with machine learning techniques. The Journal of Finance and Data Science, v. 2, n. 1, p. 42–57, mar. 2016.

FAMA, E. F. Efficient Capital Markets: A Review of Theory and Empirical Work. The Journal of Finance, v. 25, n. 2, p. 383–417, maio 1970.

GÖÇKEN, M. et al. Integrating metaheuristics and Artificial Neural Networks for improved stock price prediction. Expert Systems with Applications, v. 44, p. 320–331, fev. 2016.

HENRIQUE, B. M.; SOBREIRO, V. A.; KIMURA, H. Practical machine learning: Forecasting daily financial markets directions. Expert Systems with Applications, v. 233, p. 120840, 15 dez. 2023.

HUANG, J.-Y.; TUNG, C.-L.; LIN, W.-Z. Using Social Network Sentiment Analysis and Genetic Algorithm to Improve the Stock Prediction Accuracy of the Deep Learning-Based Approach. v. 16, n. 1, 29 maio 2023.

JIANG, J. G.; LIU, J. Predicting Stock Market N-Days Ahead Using SVM Optimized by Selective Thresholds. 15 fev. 2020.

JIANG, M. et al. A novel interval dual convolutional neural network method for interval-valued stock price prediction. Pattern Recognition, p. 109920, 26 ago. 2023.

KARA, Y.; ACAR BOYACIOGLU, M.; BAYKAN, Ö. K. Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock Exchange. Expert Systems with Applications, v. 38, n. 5, p. 5311–5319, maio 2011.

KHOA, B. T.; HUYNH, T. T. Forecasting stock price movement direction by machine learning algorithm. International Journal of Electrical and Computer Engineering (IJECE), v. 12, n. 6, p. 6625, 1 dez. 2022.

KIM, K. Financial time series forecasting using support vector machines. Neurocomputing, v. 55, n. 1-2, p. 307–319, set. 2003.

MACIEL, L. Brazilian stock-market efficiency before and after COVID-19: The roles of fractality and predictability. Global Finance Journal, p. 100887–100887, 1 ago. 2023.

NAYAK, R. K.; MISHRA, D.; RATH, A. K. A Naïve SVM-KNN based stock market trend reversal analysis for Indian benchmark indices. Applied Soft Computing, v. 35, p. 670–680, out. 2015.

PATEL, J. et al. Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniques. Expert Systems with Applications, v. 42, n. 1, p. 259–268, jan. 2015.

SCIKIT. Scikit Learn: Support Vector Machines. Disponível [link] Acessado em: 02/02/2024.

TAY, F. E. H.; CAO, L. Application of support vector machines in financial time series forecasting. Omega, v. 29, n. 4, p. 309–317, ago. 2001.

ŻBIKOWSKI, K. Using Volume Weighted Support Vector Machines with walk forward testing and feature selection for the purpose of creating stock trading strategy. Expert Systems with Applications, v. 42, n. 4, p. 1797–1805, mar. 2015.

WEINBAUM, D. et al. Option Trading Activity, News Releases, and Stock Return Predictability. Management Science, 9 set. 2022.