Search:
Match:
4 results
Paper#Finance, Machine Learning🔬 ResearchAnalyzed: Jan 3, 2026 18:37

Nonstationarity-Complexity Tradeoff in Stock Return Prediction

Published:Dec 29, 2025 16:49
1 min read
ArXiv

Analysis

This paper addresses a crucial challenge in financial time series prediction: the balance between model complexity and the impact of non-stationarity. It proposes a novel model selection method to overcome this tradeoff, demonstrating significant improvements in out-of-sample performance, especially during economic downturns. The economic impact, as evidenced by improved trading strategy returns, further validates the significance of the research.
Reference

“Our method achieves positive $R^2$ during the Gulf War recession while benchmarks are negative, and improves $R^2$ in absolute terms by at least 80bps during the 2001 recession as well as superior performance during the 2008 Financial Crisis.”

PermalinkArXiv
Research Paper#Finance, Machine Learning, Clustering🔬 ResearchAnalyzed: Jan 3, 2026 18:39

Panel Coupled Matrix-Tensor Clustering for Asset Pricing

Published:Dec 29, 2025 16:08
1 min read
ArXiv

Analysis

This paper addresses the limitations of traditional asset pricing models by introducing a novel Panel Coupled Matrix-Tensor Clustering (PMTC) model. It leverages both a characteristics tensor and a return matrix to improve clustering accuracy and factor loading estimation, particularly in noisy and sparse data scenarios. The integration of multiple data sources and the development of computationally efficient algorithms are key contributions. The empirical application to U.S. equities suggests practical value, showing improved out-of-sample performance.
Reference

“The PMTC model simultaneously leverages a characteristics tensor and a return matrix to identify latent asset groups.”

PermalinkArXiv
Research#llm🔬 ResearchAnalyzed: Dec 25, 2025 04:40

Structured Event Representation and Stock Return Predictability

Published:Dec 24, 2025 05:00
1 min read
ArXiv Stats ML

Analysis

This research paper explores the use of large language models (LLMs) to extract event features from news articles for predicting stock returns. The authors propose a novel deep learning model based on structured event representation (SER) and attention mechanisms. The key finding is that this SER-based model outperforms existing text-driven models in out-of-sample stock return forecasting. The model also offers interpretable feature structures, allowing for examination of the underlying mechanisms driving stock return predictability. This highlights the potential of LLMs and structured data in financial forecasting and provides a new approach to understanding market dynamics.
Reference

“Our SER-based model provides superior performance compared with other existing text-driven models to forecast stock returns out of sample and offers highly interpretable feature structures to examine the mechanisms underlying the stock return predictability.”

PermalinkArXiv Stats ML
Research#deep learning📝 BlogAnalyzed: Jan 3, 2026 06:22

Are Deep Neural Networks Dramatically Overfitted?

Published:Mar 14, 2019 00:00
1 min read
Lil'Log

Analysis

The article raises a fundamental question about the generalization ability of deep neural networks, given their high number of parameters and potential for perfect training error. It highlights the common concern of overfitting in deep learning.

Key Takeaways

Reference

“Since a typical deep neural network has so many parameters and training error can easily be perfect, it should surely suffer from substantial overfitting. How could it be ever generalized to out-of-sample data points?”

PermalinkLil'Log