Forecasting Price Movements using Technical Indicators: Investigating the Impact of Varying Input Window Length

Yauheniya Shynkevich, T.Martin McGinnity, Sonya Coleman, Ammar Belatreche, Yuhua Li

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

The creation of a predictive system that correctly forecasts future changes of a stock price is crucial for investment management and algorithmic trading. The use of technical analysis for financial forecasting has been successfully employed by many researchers. Input window length is a time frame parameter required to be set when calculating many technical indicators. This study explores how the performance of the predictive system depends on a combination of a forecast horizon and an input window length for forecasting variable horizons. Technical indicators are used as input features for machine learning algorithms to forecast future directions of stock price movements. The dataset consists of ten years daily price time series for fifty stocks. The highest prediction performance is observed when the input window length is approximately equal to the forecast horizon. This novel pattern is studied using multiple performance metrics: prediction accuracy, winning rate, return per trade and Sharpe ratio.
LanguageEnglish
Pages71-88
JournalNeurocomputing
Volume264
Early online date16 Jun 2017
DOIs
Publication statusE-pub ahead of print - 16 Jun 2017

Fingerprint

Research Personnel
Learning algorithms
Learning systems
Time series
Machine Learning
Datasets
Direction compound

Keywords

  • stock price prediction
  • financial forecasting
  • technical trading
  • decision making

Cite this

@article{eeccbb2fceb24b8a9e0d92c9623b4060,
title = "Forecasting Price Movements using Technical Indicators: Investigating the Impact of Varying Input Window Length",
abstract = "The creation of a predictive system that correctly forecasts future changes of a stock price is crucial for investment management and algorithmic trading. The use of technical analysis for financial forecasting has been successfully employed by many researchers. Input window length is a time frame parameter required to be set when calculating many technical indicators. This study explores how the performance of the predictive system depends on a combination of a forecast horizon and an input window length for forecasting variable horizons. Technical indicators are used as input features for machine learning algorithms to forecast future directions of stock price movements. The dataset consists of ten years daily price time series for fifty stocks. The highest prediction performance is observed when the input window length is approximately equal to the forecast horizon. This novel pattern is studied using multiple performance metrics: prediction accuracy, winning rate, return per trade and Sharpe ratio.",
keywords = "stock price prediction, financial forecasting, technical trading, decision making",
author = "Yauheniya Shynkevich and T.Martin McGinnity and Sonya Coleman and Ammar Belatreche and Yuhua Li",
year = "2017",
month = "6",
day = "16",
doi = "10.1016/j.neucom.2016.11.095",
language = "English",
volume = "264",
pages = "71--88",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

Forecasting Price Movements using Technical Indicators: Investigating the Impact of Varying Input Window Length. / Shynkevich, Yauheniya; McGinnity, T.Martin; Coleman, Sonya; Belatreche, Ammar; Li, Yuhua.

In: Neurocomputing, Vol. 264, 16.06.2017, p. 71-88.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Forecasting Price Movements using Technical Indicators: Investigating the Impact of Varying Input Window Length

AU - Shynkevich, Yauheniya

AU - McGinnity, T.Martin

AU - Coleman, Sonya

AU - Belatreche, Ammar

AU - Li, Yuhua

PY - 2017/6/16

Y1 - 2017/6/16

N2 - The creation of a predictive system that correctly forecasts future changes of a stock price is crucial for investment management and algorithmic trading. The use of technical analysis for financial forecasting has been successfully employed by many researchers. Input window length is a time frame parameter required to be set when calculating many technical indicators. This study explores how the performance of the predictive system depends on a combination of a forecast horizon and an input window length for forecasting variable horizons. Technical indicators are used as input features for machine learning algorithms to forecast future directions of stock price movements. The dataset consists of ten years daily price time series for fifty stocks. The highest prediction performance is observed when the input window length is approximately equal to the forecast horizon. This novel pattern is studied using multiple performance metrics: prediction accuracy, winning rate, return per trade and Sharpe ratio.

AB - The creation of a predictive system that correctly forecasts future changes of a stock price is crucial for investment management and algorithmic trading. The use of technical analysis for financial forecasting has been successfully employed by many researchers. Input window length is a time frame parameter required to be set when calculating many technical indicators. This study explores how the performance of the predictive system depends on a combination of a forecast horizon and an input window length for forecasting variable horizons. Technical indicators are used as input features for machine learning algorithms to forecast future directions of stock price movements. The dataset consists of ten years daily price time series for fifty stocks. The highest prediction performance is observed when the input window length is approximately equal to the forecast horizon. This novel pattern is studied using multiple performance metrics: prediction accuracy, winning rate, return per trade and Sharpe ratio.

KW - stock price prediction

KW - financial forecasting

KW - technical trading

KW - decision making

U2 - 10.1016/j.neucom.2016.11.095

DO - 10.1016/j.neucom.2016.11.095

M3 - Article

VL - 264

SP - 71

EP - 88

JO - Neurocomputing

T2 - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -