---
title: Intraday Returns Forecasting in Brazil
url: https://www.ml-quant.com/papers/ssrn/5122977/
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 5122977
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5122977
featured: 2025-02-19
citations: unknown
topic: Econometrics & Forecasting
---


# Intraday Returns Forecasting in Brazil

The study compares machine learning methods for forecasting Brazilian stock returns, with Ridge Regression performing best when considering transaction costs.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5122977
- Identifier: SSRN 5122977
- Released: 2025-02-03
- First featured: Quant Letter No. 85 (2025-02-19): https://www.ml-quant.com/issues/2025-02-19/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [Forecasting Bid–Ask Spreads in Foreign Exchange: Analysis and Machine Learning Prediction](https://www.ml-quant.com/papers/ssrn/4701477/): 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.
- [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.
- [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.
- [Contrastive Similarity Learning for Market Forecasting: The ContraSim Framework](https://www.ml-quant.com/papers/arxiv/2502.16023/): The ContraSim algorithm is introduced as a tool to understand the correlation between daily financial headlines and market movements, enhancing the precision of financial forecasting.
- [Stories that (are) Move(d by) Markets: A Causal Exploration of Market Shocks and Semantic Shifts across Different Partisan Groups](https://www.ml-quant.com/papers/arxiv/2502.14497/): The study shows a two-way link between news narratives and financial market shocks, indicating that changes in public discourse can trigger economic shifts and vice versa, with factors like partisanship and unexpected events like COVID-19 affecting this relationship.