Akcije

Scientific Publications of the State University of Novi Pazar Series A: Applied Mathematics, Informatics and mechanics
kako citirati ovaj članak
podeli ovaj članak

Metrika

  • citati u SCIndeksu: 0
  • citati u CrossRef-u:0
  • citati u Google Scholaru:[]
  • posete u poslednjih 30 dana:6
  • preuzimanja u poslednjih 30 dana:6

Sadržaj

članak: 6 od 7  
Back povratak na rezultate
Machine learning techniques for stock market trends identification
(naslov ne postoji na srpskom)
Department Financial University under the Government of the Russian Federation, Moscow, Russia
Sažetak
(ne postoji na srpskom)
The research concentrates on recognizing stock markets long-term upward and downward trends. The key results are obtained with the use of gradient boosting algorithms, XGBoost in particular. The raw data is represented by time series with basic stock market quotes with periods labelled by experts as Trend or Flat. The features are then obtained via various data transformations, aiming to catch implicit factors resulting in change of stock direction. Modelling is done in two stages: stage one aims to detect endpoints of tendencies (i.e. "sliding windows"), stage two recognizes the tendency itself inside the window. The research addresses such issues as imbalanced datasets and contradicting labels, as well as the need of specific quality metrics to keep up with practical applicability. The model can be used to design an investment strategy though further research in feature engineering and fine calibration is required.
Reference
*** XGBoost Parameters. http://xgboost.readthedocs.io/en/latest/parameter.html
Brink, H., Richards, J., Fetherolf, M. (2017) Real-World Machine Learning. USA: Manning Publications Co
Soloviev, V. (2017) Forecasting Stock Market Turnovers with Boosted Decision Trees. u: 11th International Conference on Application of Information and Communication Technologies (AICT) 2017, Proc, Vol. 1, pp. 140-143
 

O članku

jezik rada: engleski
vrsta rada: neklasifikovan
DOI: 10.5937/SPSUNP1901047Z
objavljen u SCIndeksu: 16.07.2019.

Povezani članci

Nema povezanih članaka