Applying Technical Analysis and Neural Networks for Stock Price Prediction
| Autor: | LIU, CHUN-YU, 劉峻宇 |
|---|---|
| Rok vydání: | 2018 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 106 The stock market forecasting is an important issue in financial engineering. An accurate forecasting system helps investors obtain high profit margin. With the development of technologies and the evolution of big data, the stock market investment will no longer be directly performed by the human; instead, intelligent investment will provide investors more accurate strategy analysis and more effective investment decisions. Therefore, this study proposed to combine the technical analysis pointers with the back propagation neural network. The technical analysis provided several useful functions such as stock price analysis, forecasting, and obtaining the key data in the stock price. We used the technical pointers instead of the raw data as the input variables of neural networks and verified if the pre-processing data can achieve more accurate stock price prediction. The technical analysis indicator package was written in the R language. The four major indexes of U.S stock market, Dow Jones Industrial Average, Philadelphia Semiconductor Index, Standard & Poor's 500 Index, NASDAQ Composite Index and sixteen listed companies serve as the sample data. Several kinds of pre-processing models were introduced. Through looking into the experimental results, the proposed package helped the neural networks achieve better performance. The proposed package passed a comprehensive R archive network (CRAN) check and made contribution to R in the field of stock data analysis. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|