Meta-Labeling: Calibration and Position Sizing
The Journal of Financial Data Science · 30.04.2023 · 5 (2) · 23-40
DOI: 10.3905/jfds.2023.1.119 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Financial Data Science, online erschienen am 08.03.2023. Verfasst von Michael Meyer und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Meta-labeling is a recently developed tool for determining the position size of a trade. It involves applying a secondary model to produce an output that can be interpreted as the estimated probability of a profitable trade, which can then be used to size positions. Before sizing the position, probability calibration can be applied to bring the model’s estimates closer to true posterior probabilities. This article investigates the use of these estimated probabilities, both uncalibrated and calibrated, in six position sizing algorithms. The algorithms used in this article include established methods used in practice and variations thereon, as well as a novel method called sigmoid optimal position sizing. The position sizing methods are evaluated and compared using strategy metrics such as the Sharpe ratio and maximum drawdown. The results indicate that the performance of fixed position sizing methods is significantly improved by calibration, whereas methods that estimate their functions from the training data do not gain any significant advantage from probability calibration.
Zitieren
APA
Meyer, M., Barziy, I., & Joubert, J. F. (2023). Meta-Labeling: Calibration and Position Sizing. The Journal of Financial Data Science, 5(2), 23-40. https://doi.org/10.3905/jfds.2023.1.119
Vancouver
Meyer M, Barziy I, Joubert JF. Meta-Labeling: Calibration and Position Sizing. The Journal of Financial Data Science. 2023;5(2):23-40. doi:10.3905/jfds.2023.1.119
BibTeX
@article{Meyer2023,
author = {Meyer, Michael and Barziy, Illya and Joubert, Jacques Francois},
title = {Meta-Labeling: Calibration and Position Sizing},
journal = {The Journal of Financial Data Science},
year = {2023},
volume = {5},
number = {2},
pages = {23--40},
doi = {10.3905/jfds.2023.1.119}
}
EUVIMED