Quantitative Tactical Asset Allocation Using Ensemble Machine Learning Methods
Oflus (2014) studies market timing and tactical asset allocation across several asset classes using a feedforward neural network. The abstract mentions a benchmark and transaction costs but not an out-of-sample test, multiple testing or the size of the universe.
“Our initial results show that it is possible to beat the SP500 benchmark index by 600 basis points (in the calculations industry standard trading costs are included) as it is demonstrated by comparing the overall performance of the proposed method.”
AssetMulti-asset
StrategyMarket timingmomentum
TechniqueFeedforward networktree ensemble
Also stated: benchmark, costs
Missing from abstract: out-of-sample test, 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 neighbourhoodMarket timing and tactical asset allocation by year
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 | |
|---|---|---|---|---|---|
| Deep Learning for Global Tactical Asset Allocation by Chakravorty et al. | 2018 | ||||
| Relative Sentiment and Machine Learning for Tactical Asset Allocation by Micaletti | 2019 | ||||
| The Use of Deep Reinforcement Learning in Tactical Asset Allocation by Katongo and Bhattacharyya | 2021 | ||||
| Beyond Binary: A Ternary Regime Framework for Tactical Asset Allocation by Richman | 2026 | ||||
| A Unified Theory of Strategic and Tactical Asset Allocation by Alonso | 2026 |