Interpretable Factors of Firm Characteristics

TL;DR

This paper introduces a new method for creating interpretable financial factors from firm characteristics by combining economic intuition with data-driven clustering, resulting in more meaningful and effective factors.

Contribution

The paper proposes a novel framework that groups related characteristics to derive interpretable factors, improving upon existing statistical and economic modeling approaches.

Findings

Economically meaningful factors match or outperform standard IPCA in pricing.

Parsimonious factors derived from 94 characteristics outperform benchmarks in out-of-sample tests.

Embedding economic structure enhances the interpretability and performance of factors.

Abstract

We develop a new framework for constructing factors from firm characteristics that balances statistical efficiency and economic interpretability. Instead of using all characteristics equally, our method groups related characteristics and derives one factor per group. The grouping combines economic intuition with data-driven clustering. Applied to the IPCA model by Kelly et al. (2019), our approach yields economically meaningful factors that match or exceed standard IPCA in pricing performance. Using 94 characteristics from Gu et al. (2020), we show that our parsimonious, transparent factors outperform benchmarks in out-of-sample tests, demonstrating the value of embedding economic structure into statistical modeling.