Name
Title | ||
|---|---|---|
Forecasting price movements using technical indicators: Investigating the impact of varying input window length. |
Abstract | ||
|---|---|---|
•We use technical indicators computed from historical prices to predict stock price movements.•The effect of choosing different values of the time frame for computing technical indicators called window size is examined.•We investigate how the performance of a machine-learning predictive system depends on a forecast horizon and a window size.•The novel pattern is revealed: the highest prediction performance is reached when the window size is equal to the horizon.•Several performance metrics are used: prediction accuracy, winning rate, return per trade and Sharpe ratio. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1016/j.neucom.2016.11.095 | Neurocomputing |
Keywords | Field | DocType |
Stock price prediction,Financial forecasting,Technical trading,Decision making | Econometrics,Financial forecasting,Stock price,Actuarial science,Time frame,Artificial intelligence,Investment management,Algorithmic trading,Technical analysis,Sharpe ratio,Stock (geology),Mathematics,Machine learning | Journal |
Volume | ISSN | Citations |
264 | 0925-2312 | 9 |
PageRank | References | Authors |
0.54 | 13 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yauheniya Shynkevich | 1 | 24 | 2.34 |
| T. Martin Mcginnity | 2 | 518 | 66.30 |
| Sonya Coleman | 3 | 216 | 36.84 |
| A. Belatreche | 4 | 165 | 12.40 |
| Yuhua Li | 5 | 1113 | 53.63 |