Machine Learning on Stock Price Movement Forecasts: The Case of Stocks in Taiwan Stock Exchange
| Autor: | LIU, YI-SHENG, 劉譯聲 |
|---|---|
| Rok vydání: | 2019 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 107 This paper addresses the problem of predicting the movement direction of stock price index in the Taiwan stock market. The study compares four prediction models consisting of Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest and Naive-Bayes with two approaches applied to these models. The first data preprocess approach involves computation of ten technical parameters using stock trading data while the second approach focuses on representing these technical parameters as trend deterministic data. Accuracy of each of the prediction models for each of the two input approaches is evaluated. Evaluation is carried out on 19 years of historical data from 2000 to 2018 of Taiwan Stock Market Index. The experimental results show that for the first approach of input data, ten technical parameters are expressed as continuous values, and the ANN is superior to the other three prediction models in overall performance. Experimental results also show that the performance of all the prediction models improves when these technical parameters are represented as binary trend deterministic data. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|