Stock Market Data Prediction Using Machine Learning Techniques
Abstract
This paper studies the possibilities of making prediction of stock market prices using historical data and machine learning algorithms. We have experimented with stock market data of the Apple Inc. using random trees and multilayer perceptron algorithms to perform the predictions of closing prices. An accuracy analysis was also conducted to determine how useful can these types of supervised machine learning algorithms could be in the financial field. These types of studies could also be researched with data from the Ecuadorian stock market exchanges i.e. Bolsa de Valores de Quito (BVQ) and Bolsa de Valores de Guayaquil (BVG) to evaluate the effectiveness of the algorithms in less liquid markets and possibly help reduce inefficiency costs for market participants and stakeholders.
Keywords
Machine learning Stock market Artificial intelligence PredictionReferences
- 1.Schumacher, R.P., Chen, H.: Textual analysis of stock market prediction using breaking financial news: the AZFin text system. ACM Trans. Inf. Syst. 27, 1–19 (2009)CrossRefGoogle Scholar
- 2.Giannini, R.C., Irvine, P.J., Shu, T.: Do local investors know more? A direct examination of individual investors’ information set. Working paper (2014)Google Scholar
- 3.Bar-Haim, R., Dinur, E., Feldman, R., Fresko, M., Goldstein, G.: Identifying and following expert investors in stock microblogs. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 1310–1319 (2011)Google Scholar
- 4.Plakandaras, V., Papadimitriou, T., Gogas, P., Diamantaras, K.: Market sentiment and exchange rate directional forecasting. Algorithmic Financ. 4(1–2), 69–79 (2015)MathSciNetGoogle Scholar
- 5.Ruiz-Martínez, J.M., Valencia-García, R., García-Sánchez, F.: Semantic-based sentiment analysis in financial news. In Proceedings of the 1st International Workshop on Finance and Economics on the Semantic Web, pp. 38–51 (2012)Google Scholar
- 6.Kumar, A., Malik, H., Chandel, S.S.: Selection of most relevant input parameters using WEKA for artificial neural network based solar radiation prediction models. Renew. Sustain. Energy Rev. 31, 509–519 (2014)CrossRefGoogle Scholar
- 7.Kalmegh, S.: Analysis of WEKA data mining algorithm REPTree, Simple Cart and RandomTree for classification of indian new. Int. J. Innov. Sci. Eng. Technol. 2(2), 438–446 (2015)Google Scholar
- 8.Teuvo, K.: Self-Organizing Maps. Springer Science & Business Media, Heidelberg (2001)zbMATHGoogle Scholar
- 9.Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice-Hall, Upper Saddle River (1995)zbMATHGoogle Scholar
- 10.Aha, D.W.: Tolerating noisy, irrelevant, and novel attributes in instance based learning algorithms. Int. J. Man Mach. Stud. 36(2), 267–287 (1992)CrossRefGoogle Scholar
- 11.Wettschereck, D., Aha, D.W., Mohri, T.: A review and empirical evaluation of feature weighting methods for a class of lazy learning algorithms. Artif. Intell. Rev. 11(1–5), 273–314 (1997)CrossRefGoogle Scholar
- 12.Hornik, K., Buchta, C., Zeileis, A.: Open-source machine learning: R meets weka. Comput. Stat. 24(2), 225–232 (2009)MathSciNetCrossRefGoogle Scholar
- 13.Fama, E.F.: Random walks in sotck market prices. Financ. Anal. J. 51(1), 75–80 (1995)CrossRefGoogle Scholar
- 14.Osborne, M.F.M.: Brownian motion in the stock market. Oper. Res. 7(2), 145–173 (1959)MathSciNetCrossRefGoogle Scholar