Advanced search
Add to list

Equity price direction prediction for day trading ensemble classification using technical analysis indicators with interaction effects

Author
Organization
Abstract
We investigate the performance of complex trading rules in equity price direction prediction, over and above continuous-valued indicators and simple technical trading rules. Ten of the most popular technical analysis indicators are included in this research. We use Random Forest ensemble classifiers using minute-by-minute stock market data. Results show that our models have predictive power and yield better returns than the buy-and-hold strategy when disregarding transaction costs both in terms of number of stocks with profitable trades as well as overall returns. Moreover, our findings show that two-way and three-way combinations, i.e., complex trading rules, are important to "beat" the buy-and-hold strategy.
Keywords
STOCK TREND PREDICTION, RETURNS, MACHINE, NETWORK, RULES, day trading, equity price direction prediction, technical analysis, stock trading, ensemble classification, systematic trading, quantitative, analysis, big data analytics

Citation

Please use this url to cite or link to this publication:

MLA
Van den Poel, Dirk et al. “Equity Price Direction Prediction for Day Trading Ensemble Classification Using Technical Analysis Indicators with Interaction Effects.” 2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC). 2016. 3455–3462. Print.
APA
Van den Poel, D., Chesterman, C., Koppen, M., & Ballings, M. (2016). Equity price direction prediction for day trading ensemble classification using technical analysis indicators with interaction effects. 2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (pp. 3455–3462). Presented at the IEEE Congress on Evolutionary Computation (CEC) held as part of IEEE World Congress on Computational Intelligence (IEEE WCCI).
Chicago author-date
Van den Poel, Dirk, Celine Chesterman, Maxim Koppen, and Michel Ballings. 2016. “Equity Price Direction Prediction for Day Trading Ensemble Classification Using Technical Analysis Indicators with Interaction Effects.” In 2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 3455–3462.
Chicago author-date (all authors)
Van den Poel, Dirk, Celine Chesterman, Maxim Koppen, and Michel Ballings. 2016. “Equity Price Direction Prediction for Day Trading Ensemble Classification Using Technical Analysis Indicators with Interaction Effects.” In 2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 3455–3462.
Vancouver
1.
Van den Poel D, Chesterman C, Koppen M, Ballings M. Equity price direction prediction for day trading ensemble classification using technical analysis indicators with interaction effects. 2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC). 2016. p. 3455–62.
IEEE
[1]
D. Van den Poel, C. Chesterman, M. Koppen, and M. Ballings, “Equity price direction prediction for day trading ensemble classification using technical analysis indicators with interaction effects,” in 2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), Vancouver, CANADA, 2016, pp. 3455–3462.
@inproceedings{8541237,
  abstract     = {We investigate the performance of complex trading rules in equity price direction prediction, over and above continuous-valued indicators and simple technical trading rules. Ten of the most popular technical analysis indicators are included in this research. We use Random Forest ensemble classifiers using minute-by-minute stock market data. Results show that our models have predictive power and yield better returns than the buy-and-hold strategy when disregarding transaction costs both in terms of number of stocks with profitable trades as well as overall returns. Moreover, our findings show that two-way and three-way combinations, i.e., complex trading rules, are important to "beat" the buy-and-hold strategy.},
  author       = {Van den Poel, Dirk and Chesterman, Celine and Koppen, Maxim and Ballings, Michel},
  booktitle    = {2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC)},
  isbn         = {9781509006229},
  keywords     = {STOCK TREND PREDICTION,RETURNS,MACHINE,NETWORK,RULES,day trading,equity price direction prediction,technical analysis,stock trading,ensemble classification,systematic trading,quantitative,analysis,big data analytics},
  language     = {eng},
  location     = {Vancouver, CANADA},
  pages        = {3455--3462},
  title        = {Equity price direction prediction for day trading ensemble classification using technical analysis indicators with interaction effects},
  year         = {2016},
}

Web of Science
Times cited: