人力资本与劳动经济研究中心

Center for Human Capital and Labor Market Research

Applied Microeconomics Seminar Series

Fall 2025

讲座题目：Image-Based Asset Pricing in Commodity Futures Market

报告人: 贾越珵

内容摘要：We introduce a deep visualization (DV) framework that turns conventional commodity data into images and extracts predictive signals via convolutional feature learning. Specifically, we encode the futures term structure as images and derive two deep‑visualization (DV) predictors, carry (bsDV), basis momentum (bmDV), each of which consistently outperforms its traditional formula‑based counterpart in return predictability. By forming long–short portfolios in the top (bottom) quartile of each DV predictor, we build an image‑based factor model that delivers significant alpha and better explains the cross‑section of commodity returns than existing benchmarks. Our findings reveal that transforming conventional financial data into images and relying solely on image-derived features suffices to construct a sophisticated asset pricing model at least in commodity markets, pioneering the paradigm of image‑based asset pricing.

报告人简介： 贾越珵，中央财经大学中国金融发展研究院副教授。主要研究领域包括资产定价，深度学习，大宗商品，和量化投资实践。学术论文发表于Journal of Banking and Finance (2篇), Journal of Empirical Finance，European Financial Management (2篇), Pacific-Basin Finance Journal等国际权威刊物。另有多篇论文在国际顶级和权威期刊送审后修订并重新提交。2018年以来深耕量化投资领域，在头部量化私募任核心投研与股票量化策略投资经理，管理多只私募产品。精通Python和C++编程在量化投资实践中的应用。

时间：2025.10.29 周三12:30-13:45

地点：学术会堂（南楼）608

撰稿人：邱南沙

审稿人：汪雪菲