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.
Key Takeaways
- •Introduces the Panel Coupled Matrix-Tensor Clustering (PMTC) model for asset pricing.
- •Integrates a characteristics tensor and a return matrix for improved clustering and factor loading estimation.
- •Outperforms single-source alternatives in simulations.
- •Demonstrates practical value with improved out-of-sample performance in U.S. equities.
Reference
“The PMTC model simultaneously leverages a characteristics tensor and a return matrix to identify latent asset groups.”