Signals in the Noise: A Machine-Learning Approach to Pricing Alternative Information Shocks in Chinese Agricultural Futures
Published in Journal of Futures Markets (JCR Q2) — under review, 2026
Alternative and unstructured information is abundant in Chinese agricultural futures markets, but most of it is noise. This paper uses machine-learning methods to isolate the component that is genuinely priced, and characterises the conditions under which alternative information shocks carry signal.
Status: under review at the Journal of Futures Markets.
Recommended citation: Chen, A.W., Chen, X. & Zhu, Z.* (2026). "Signals in the Noise: A Machine-Learning Approach to Pricing Alternative Information Shocks in Chinese Agricultural Futures." Journal of Futures Markets, under review.
Download Paper