---
title: Forecasting Bid–Ask Spreads in Foreign Exchange: Analysis and Machine Learning Prediction
url: https://www.ml-quant.com/papers/ssrn/4701477/
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 4701477
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4701477
featured: 2024-01-23
citations: 1
topic: Econometrics & Forecasting
---


# Forecasting Bid–Ask Spreads in Foreign Exchange: Analysis and Machine Learning Prediction

Machine learning algorithms can effectively predict transaction costs in the foreign exchange market, which can greatly vary based on factors like time of day or week.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4701477
- Identifier: SSRN 4701477
- Released: 2024-01-20
- First featured: Quant Letter No. 34 (2024-01-23): https://www.ml-quant.com/issues/2024-01-23/
- Citations (Semantic Scholar): 1
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [Earnings Forecast Accuracy](https://www.ml-quant.com/papers/ssrn/4827682/): The study examines the link between model-based earnings forecast accuracy and portfolios sorted on implied cost of capital, highlighting that machine learning models provide the highest return spreads and the importance of considering transaction costs in financial analysis.
- [Intraday Returns Forecasting in Brazil](https://www.ml-quant.com/papers/ssrn/5122977/): The study compares machine learning methods for forecasting Brazilian stock returns, with Ridge Regression performing best when considering transaction costs.
- [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.
- [Deep Generative Modeling for Financial Time Series with Application in VaR: A Comparative Review](https://www.ml-quant.com/papers/arxiv/2401.10370/): The paper introduces new methods for conditional time series generation in financial risk modeling using deep generative methods, and presents a framework to assess the quality of the generated series.
- [The econometrics of happiness: Are We Underestimating the Returns to Education and Income?](https://www.ml-quant.com/papers/arxiv/1807.11835/): Value Rounding Behavior: The study addresses the issue of response scale simplification in surveys, particularly by less educated respondents, and introduces a model to estimate latent subjective wellbeing.