Stock Market Data Prediction Using Machine Learning Techniques
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.
KeywordsMachine learning Stock market Artificial intelligence Prediction
- 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
- 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
- 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