Abstract Stock market movement follows the random walk nature. The technical analysis incorporates the use of various technical indicators. Technical analysis is well suited for short term predictions. In this research work, Machine learning algorithms - Decision Tree, Support Vector Machine, Naïve Bayes and Deep Learning algorithms- Convolutional Neural Networks and Generative Adversarial Networks are used for the stock market prediction problem. Datasets of three companies- Maruti Suzuki, HDFC and Infosys belonging to Automobile, Banking and IT sector listed on National Stock Exchange (NSE) - Indian stock market over the period of 6 years (June 2014-June 2020) are considered. Performance of the above algorithms is measured in terms of how accurately they predict the stock movements. For the construction of learning models cross validation as well as training-testing percentage split are used. From the results, it is clear that deep learning algorithms show better prediction accuracy as compared to machine learning models.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|