Prediction stock price movement using subsethood and weighted subsethood fuzzy time series models
Forecasting is the prediction process for the future value. The closing price is usually used to forecast stock price movement in the next period. Predicted stock prices in the investment world become an important thing for stock trading activities. The forecasting process can be the most challengin...
Saved in:
| Main Authors: | , , |
|---|---|
| 格式: | Article |
| 語言: | English |
| 出版: |
AIP Publishing LLC
2019
|
| 主題: | |
| 在線閱讀: | http://repo.uum.edu.my/26977/1/AIP%202019%201%206.pdf http://repo.uum.edu.my/26977/ http://doi.org/10.1063/1.5121123 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | Forecasting is the prediction process for the future value. The closing price is usually used to forecast stock price movement in the next period. Predicted stock prices in the investment world become an important thing for stock trading activities. The forecasting process can be the most challenging problems due to difficulty and uncertainty of stock market because stock markets are essentially complex, dynamic, and usually in a nonlinear pattern. One of the novel forecasting methods in this area is fuzzy time series (FTS). This paper proposed stock price movement forecasting using first order and high order weighted subsethood fuzzy time series (WeSuFTS) and subsethood fuzzy time series (SuFTS) methods. A set of secondary data gained from the Kuala Lumpur Stock Exchange (KLSE) website. We chose Malaysian Resources Corp Bhd and we collected the historical data for two months,which is on a day-to-day basis. The performance of four models was analyzed using absolute percentage error (APE), mean square error (MSE), mean absolute percentage error (MAPE) and root mean squared error (RMSE). From the evaluation part of data, the results revealed second order SuFTS is the best model to forecast stock price movement with forecasting error from 0.66% - 6.44% (APE), 2.43% (MAPE), 0.00042 (MSE) and 0.0205 (RMSE). |
|---|