Machine learning in corporate bonds: Evidence from China
研究用多种机器学习方法分析中国公司债收益率的截面差异，发现机器学习优于传统线性模型，尤其能捕捉国企主导、隐性担保等市场特征，并比较了多空与纯多策略。
This study employs a broad set of machine learning (ML) methods to examine cross-sectional variation in corporate bond returns in China. Using macroeconomic indicators together with bond- and issuer-specific characteristics, we find that ML techniques outperform traditional linear models in both statistical and economic terms. These models are particularly effective at capturing distinctive features of the Chinese market, including the dominance of state-owned enterprises, implicit government guarantees, and rapid market evolution. We compare long-short and long-only portfolio strategies to account for practical constraints on short selling. The results indicate that ML methods are effective in markets where institutional features and information asymmetries play a central role in asset pricing.