Users' online behavior, generated from endpoints of e-commerce website and app, is regarded as big data which can create large business value by mining them to acquire insights of users' preference, inclination and purpose. A good ranking result of product search and product assortment in online category classification can lift user's click rate, increase purchasing conversion rate and improve customer online experience. In this paper, we will introduce an online product based learning to rank model to intelligently learn product ranking. A big data architecture will also be introduced to implement this learning to rank model which analyzes huge amount of users' online behavior.