Investing Through Economic Cycles with Ensemble Machine Learning Algorithms

Thomas Raffinot and Sylvain Benoît
Additional contact information
Thomas Raffinot: LEDa - Laboratoire d'Economie de Dauphine - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres
Sylvain Benoît: LEDa - Laboratoire d'Economie de Dauphine - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres

Working Papers from HAL

Abstract: Ensemble machine learning algorithms (random forest and boosting) are applied to quickly and accurately detect economic turning points in the United States and in the Eurozone over the past three decades. The two key features of those algorithms are their abilities (i) to entertain a large number of predictors and (ii) to perform both variable selection and estimation simultaneously. The real-time ability to nowcast economic turning points is gauged by using investment strategies based on economic regimes induced by our models. When comparing predictive accuracy and profit measures, the model confidence set procedure is applied to avoid data snooping. We show that such investment strategies achieve impressive risk-adjusted returns: timing the market is thus possible.

Keywords: Random Forest; Boosting; Economic cycles; Profit maximization measures; Model Confidence Set; Machine Learning; Turning Points Detection (search for similar items in EconPapers)
Date: 2019-09-19
References: Add references at CitEc
Citations: View citations in EconPapers (2)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:wpaper:hal-02292317

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().