Improving Deep Learning of Alpha Term Structures from the Order Book
Kolm and Westray (2024) study machine learning return prediction in bonds and credit using a recurrent neural network. The abstract mentions alpha but not a benchmark, an out-of-sample test, transaction costs, multiple testing or the size of the universe.
“We evaluate the effectiveness of four DL models in forecasting high-frequency alpha term structures across various settings: a simple LSTM, a multi-head LSTM, an LSTM Seq2Seq without attention, and an LSTM Seq2Seq with attention.”
AssetBonds and credit
StrategyMachine learning
TechniqueRecurrent neural networkfeedforward network
FrequencyIntraday
Also stated: Alpha, Order book
Missing from abstract: benchmark, out-of-sample test, 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 neighbourhoodMachine learning return prediction 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 | |
|---|---|---|---|---|---|
| Real-Time Macro Information and Bond Return Predictability: A Weighted Group Deep Learning Approach by Fan et al. | 2020 | ||||
| Spatiotemporal Signals in Residuals: A Two-Stage Boosting Graph Neural Network for Stock Return Prediction by Liu et al. | 2026 | ||||
| Predicting Individual Corporate Bond Returns by He et al. | 2023 | ||||
| Predicting Corporate Bond Returns: Merton Meets Machine Learning by Bali et al. | 2020 | ||||
| Machine Learning for Cross-Sectional Return Prediction: A Comparative Study of US and Indian Equities by Khatu | 2026 |