Machine learning model with technical analysis for stock price prediction: Empirical study of Semiconductor Company in Taiwan
| Autor: | Po-Chao Lan, Yi-Hsien Wang, Wen-Cheng Hu, Yao-Lun Ou, Chun-Yueh Lin, Wei-Ling Kung |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0209 industrial biotechnology
media_common.quotation_subject Closing (real estate) Financial market Sample (statistics) 02 engineering and technology Variable (computer science) 020901 industrial engineering & automation Empirical research Work (electrical) Technical analysis 0202 electrical engineering electronic engineering information engineering Econometrics 020201 artificial intelligence & image processing Stock market Business media_common |
| Zdroj: | ISPACS |
| DOI: | 10.1109/ispacs48206.2019.8986293 |
| Popis: | The stock market was affected by different variables, such as the overall economic situation, political events, Sino-US relations and corporate operations. Therefore, if you want to get returns in the stock market, predicting the time series of financial markets in advance is the most important thing for analysts and investors. However, predicting the direction of the stock market need to access information from existing markets and past historical data. Under such complicated work and costs, it is always the most difficult and important issue to achieve accurate forecasting and reduce forecasting costs. In this paper, the backpropagation neural network is used as a research tool to analyze the historical data of Taiwan Semiconductor Manufacturing Company (hereinafter referred to as TSMC) during the sample period from 2014 to 2018. In this study, the standardized technical analysis indicators and the related variables of TSMC are taken as input variables, and the closing price of the next day is taken as the output variable to predict the closing price for TSMC of the next day. The empirical results confirm that this method does improve the forecast of stock price of TSMC. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|