Speaker "Shreyansh Gandhi" Details Back



IMAGE MATTERS - How Walmart Uses Machine Learning in Computer Vision to Serve and Protect Customers


In e-commerce, content quality of the product catalog plays a key role in delivering a satisfactory experience to the customers. In particular, visual content such as product images influences customers’ engagement and purchase decisions. In this talk, we present a machine learning driven - Visual Content Management system for extremely large e-commerce catalogs. For a given product, the system aggregates images from various sources and detects non-compliant images. We will discuss the system which detects Offensive Images and removes them to protect our customers. This system also understands and analyzes the remaining images to produce a superior image set with optimal count and quality, and arranges them in an order tailored to the demands of the customers. The system makes use of an array of technologies, ranging from deep learning to traditional computer vision, at different stages of analysis. In this talk, we will outline how the system works and discuss the unique challenges related to applying machine learning techniques to real-world data from e-commerce domain. We emphasize how we tune state-of-the-art image classification & object detection techniques to develop solutions custom made for a massive, diverse, and constantly evolving product catalog.


Shreyansh Gandhi is Principal Data Scientist at WalmartLabs and leads Product Catalog Data Science team. His team works on Offensive Image Detection, Optimal Image Selection, Visual Search, Product Categorization/ Matching/ Variant Grouping, Attribute Extraction and Product Graph. Shreyansh has extensive experience in building and operating web-scale data science and business platforms, as well as building world-class, agile, distributed teams. Prior to this, he worked on AWS EC2 at Amazon. Shreyansh holds MS in Computer Science from Georgia Tech and BTech from VJTI, India.