An unbiased Neural Ranking Model for Product Search

At Otto, we are currently testing neural networks for the LTR task due to their success in other machine learning areas. In order to serve diverse customer needs and satisfy the big data requirements of deep neural networks, we leverage multiple implicit customer feedbacks like clicks and orders from our tracklogs. Since such signals exhibit a strong bias towards the current ranking, we train a separate bias-estimator to cancel out this so-called position bias. Moreover, our architecture comprises of an encoder, which generates embeddings of user queries and product descriptions to compare their similarity beyond exact text matches. In the end, a transformer-based scoring function that models competition between products in the SERP provides the final ranking score. To learn from the different relevance signals prevalent in our tracklogs, the ranking function is embedded in a multitask learning framework.

Laurin Luttman

Otto

Laurin is a working student in the business intelligence division of Otto with more than 3 years of practical experience in the field of machine learning. Besides Otto, he has gained practical data science experience at Deloitte and VW. Moreover, he pursues his master’s degree in Data Science from the Leuphana University in Lüneburg. His master thesis “An unbiased Neural Ranking Model for Product Search” builds the basis for this talk.