Leveraging the Power of Images in Managing Product Return Rates
研究利用产品图像预测单个商品的退货率，并结合机器学习工具解释自动提取的图像特征，帮助电商管理者降低退货成本。
We use product images to predict individual item return rates, and we complement machine-based prediction with tools to interpret automatically extracted image-based interpretable features.