Transformer-based Recommenders for E-commerce



Transformer models for Natural Language Processing have exceeded human baselines. At the same time, demand for e-commerce has significantly increased. Understanding customer browsing and purchase behavior have become a key aspect of Artificial Intelligence. In this presentation, we will see how to unleash the ability of transformers models to predict sequences on an e-commerce case study and make recommendations. The presentation will first begin with an introduction to optimal transport and its influence on artificial intelligence. We will then go through Python/Pytorch examples of how to train a transformer and then apply it to the IoT delivery flow of e-commerce. Finally, we will see how to optimize e-commerce with the trained transformer and make recommendations for a consumer. Consumers will spend less time browsing to find what they are looking for online and reach optimal products or services. By the end of the presentation, you will know where artificial intelligence stands in the Fourth Industrial Revolution and put transformer models to use.


The presentation will be explained so that anybody can follow it. There are no pre-requisites.

Video URL:

Content URLs:

Speaker Info:

Denis Rothman graduated from Sorbonne University and Paris Diderot University, designing one of the very first word2matrix patented embedding and vectorizing systems. He began his career authoring one of the first AI cognitive Natural Language Processing (NLP) chatbots applied as an automated language teacher for Moët et Chandon and other companies. He has authored an AI resource optimizer for IBM and apparel producers and an advanced planning and scheduling (APS) solution used worldwide.

Speaker Links:

Section: Embedded Python and IOT
Type: Talks
Target Audience: Advanced
Last Updated: