---
title: Machine Learning Anomalies
url: https://www.ml-quant.com/papers/ssrn/4972254/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4972254
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4972254
featured: 2024-10-03
citations: unknown
topic: Asset Pricing & Factors
---


# Machine Learning Anomalies

Research indicates that return volatility and liquidity volatility, rather than momentum variables, are crucial for machine learning portfolio performance, with fundamental variables also being important.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4972254
- Identifier: SSRN 4972254
- Released: 2024-10-01
- First featured: Quant Letter No. 68 (2024-10-03): https://www.ml-quant.com/issues/2024-10-03/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Asset Pricing & Factors

## Related

- [A Capital Asset Pricing Model with Idiosyncratic Tail Risk: Comovement of Momentum and Low Risk Anomalies](https://www.ml-quant.com/papers/ssrn/4680248/): Momentum and Low Risk Anomalies: The new model expands the traditional Capital Asset Pricing Model (CAPM) by factoring in idiosyncratic tail risk, explaining momentum in stock returns and low risk anomalies.
- [NUMOSIM: A Synthetic Mobility Dataset with Anomaly Detection Benchmarks](https://www.ml-quant.com/papers/arxiv/2409.03024/): A Synthetic Mobility Dataset: The paper presents NUMOSIM, a synthetic mobility dataset for testing anomaly detection techniques, simulating realistic mobility scenarios and anomalies to improve geospatial mobility analysis.
- [Commodity Futures Characteristics and Asset Pricing Models](https://www.ml-quant.com/papers/ssrn/4746258/): The article shows that a latent-factor model using the Instrumented Principal Component Analysis methodology surpasses existing models in explaining variations in commodity futures returns, with momentum, expected shortfall, and idiosyncratic volatility as key factors.
- [Machine Learning and the Cross-Section of Emerging Market Corporate Bond Returns](https://www.ml-quant.com/papers/ssrn/4632924/): Machine learning models considering nonlinearities and interactions offer better predictions of corporate bond behavior in emerging markets with high transaction costs, with key predictors tied to low-risk macro and momentum factors.
- [Are Penalty Shootouts Better Than a Coin Toss? Evidence From International Club Football in Europe](https://www.ml-quant.com/papers/arxiv/2510.17641/): Using UEFA penalty shootout data (2000–2025) we find outcomes are essentially random—no measurable advantage from kicking order, venue, momentum, or team strength.
- [Learning to Learn Financial Networks for Optimising Momentum Strategies](https://www.ml-quant.com/papers/arxiv/2308.12212/): The L2GMOM machine learning framework enhances portfolio profitability and risk management by learning financial networks and optimizing trading signals.