---
title: Machine Learning for Financial Forecasting
url: https://www.ml-quant.com/papers/repec/eme-regepp-rege-05-2022-0079/
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: RePEc:eme:regepp:rege-05-2022-0079
source_url: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.emerald.com%2Finsight%2Fcontent%2Fdoi%2F10.1108%2FREGE-05-2022-0079%2Ffull%2Fhtml%3Futm_source%3Drepec%26utm_medium%3Dfeed%26utm_campaign%3Drepec%3Bh%3Drepec%3Aeme%3Aregepp%3Arege-05-2022-0079
featured: 2024-06-20
citations: unknown
topic: Econometrics & Forecasting
---


# Machine Learning for Financial Forecasting

Machine learning models performed better than market benchmarks during the Russia-Ukraine war, but not prior to the conflict, indicating caution should be used when forecasting stock prices with these models.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.emerald.com%2Finsight%2Fcontent%2Fdoi%2F10.1108%2FREGE-05-2022-0079%2Ffull%2Fhtml%3Futm_source%3Drepec%26utm_medium%3Dfeed%26utm_campaign%3Drepec%3Bh%3Drepec%3Aeme%3Aregepp%3Arege-05-2022-0079
- Identifier: RePEc:eme:regepp:rege-05-2022-0079
- Released: 2024-06-20
- First featured: Quant Letter No. 54 (2024-06-20): https://www.ml-quant.com/issues/2024-06-20/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [Regime Switching in Commodity Prices](https://www.ml-quant.com/papers/repec/taf-apeclt-v-31-y-2024-i-4-p-338-345/): A study from 1959 to 2022 using a 3-state Markov-switching model found that oil prices are more volatile than copper prices, reacting more to market cartelization, war episodes, and global demand shifts.
- [TKAN: Temporal Kolmogorov-Arnold Networks](https://www.ml-quant.com/papers/ssrn/4825654/): The article presents Temporal Kolomogorov-Arnold Networks (TKANs), a new neural network design that merges the benefits of Recurrent Neural Networks and Long Short-Term Memory for improved multistep time series forecasting.
- [Robust agents learn causal world models](https://www.ml-quant.com/papers/arxiv/2402.10877/): The research suggests that intelligent agents must learn an approximate causal model to generalize to new domains, impacting fields like transfer learning and causal inference.
- [Universal randomised signatures for generative time series modelling](https://www.ml-quant.com/papers/arxiv/2406.10214/): The article presents a new model for analyzing financial data over time, using a unique Wasserstein-type distance method, and compares its performance with current standards.
- [Cost-aware Bayesian optimization via the Pandora's Box Gittins index](https://www.ml-quant.com/papers/arxiv/2406.20062/): The paper suggests using the Gittins index from the Pandora's Box problem in economics as a function for cost-aware Bayesian optimization.
- [Distributional Refinement Network: Distributional Forecasting via Deep Learning](https://www.ml-quant.com/papers/arxiv/2406.00998/): The article introduces the Distributional Refinement Network (DRN), a model that enhances predictive performance and interpretability in actuarial modelling by merging a baseline model with a flexible neural network.