Optimizing Gross Merchandise Volume via DNN-MAB Dynamic Ranking Paradigm
This addresses the need for precise and responsive ranking strategies in large-scale e-commerce platforms with over 236 million daily active users, though it appears incremental as it builds on existing DNN and MAB methods.
The paper tackles the problem of optimizing gross merchandise volume (GMV) in e-commerce recommender systems by proposing DNN-MAB, a dynamic ranking paradigm that combines a pairwise deep neural network pre-ranker with a revised multi-armed bandit post-ranker, resulting in significant GMV lift compared to state-of-the-art models in production deployment.
With the transition from people's traditional `brick-and-mortar' shopping to online mobile shopping patterns in web 2.0 $\mathit{era}$, the recommender system plays a critical role in E-Commerce and E-Retails. This is especially true when designing this system for more than $\mathbf{236~million}$ daily active users. Ranking strategy, the key module of the recommender system, needs to be precise, accurate, and responsive for estimating customers' intents. We propose a dynamic ranking paradigm, named as DNN-MAB, that is composed of a pairwise deep neural network (DNN) $\mathit{pre}$-ranker connecting a revised multi-armed bandit (MAB) dynamic $\mathit{post}$-ranker. By taking into account of explicit and implicit user feedbacks such as impressions, clicks, conversions, etc. DNN-MAB is able to adjust DNN $\mathit{pre}$-ranking scores to assist customers locating items they are interested in most so that they can converge quickly and frequently. To the best of our knowledge, frameworks like DNN-MAB have not been discussed in the previous literature to either E-Commerce or machine learning audiences. In practice, DNN-MAB has been deployed to production and it easily outperforms against other state-of-the-art models by significantly lifting the gross merchandise volume (GMV) which is the objective metrics at JD.