Timing Currency Factors with Machine Learning
“The dollar factor calculated from the subset of Developed Market currencies can be timed with substantial economic significance: the Sharpe ratio improvement is around 0.4 for the best linear and 0.5 for the best non-linear model compared to a factor-carry benchmark.”
AssetCurrenciesoptions, bonds
StrategyCarry trademacro signals
TechniqueTree ensemblelinear factor model
GeographyGlobal
Also stated: 2012–2024, Sharpe ratio, Fundamentals, Macro, Options-implied, out-of-sample test
Missing from abstract: benchmark, costs, multiple testing, universe
Institutional-grade audit of this strategy.
£5 — Request the audit- Audit of the paper claims accounting for costs, luck, crises, originality, geography, etc.
- Reproduction code integratable into Bloomberg, IBKR, etc.
- Bias-free datasets for backtesting included
- Delivered in 2 working days
The paper's neighbourhoodCarry trade by year
FamilyCarry trade17Momentum and trend following289Factor investing240Machine learning return prediction15318 more · 985
AssetCurrencies13
The family is counted across the whole universe. Asset, method and authors are counted inside the family.
| Similar papers | citation | same method | same asset | same authors | |
|---|---|---|---|---|---|
| Global Currency Misalignments, Crash Sensitivity, and Moment Risk Premia by Huang and MacDonald | 2014 | ||||
| The Cross-Section of Currency Volatility by Rasekhschaffe | 2012 | ||||
| Understanding the Sources of Risk Underlying the Cross-Section of Commodity Returns by Bakshi et al. | 2015 | ||||
| Information-Geometric Phase Transitions in Currency Markets: Curvature-Driven Detection and Early Warning of Carry Trade Crashes in USD/JPY by Shah and Solanki | 2026 | ||||
| The Impact of Currency Carry Trade Activity on the Transmission of Monetary Policy by Böck et al. | 2023 |