Similar goods search based on FAISS

Abstract

Problem. The problem of obtaining a complete set of similar goods from different manufacturers based on the image and description of the product is relevant and interesting. The article includes description of algo and architecture solution for online goods clustering. Goal. The goal of the work is to create and explore models of e-commerce ML (online goods clustering). The work includes developing AI components based on FAISS and Deep Learning to implement Product Quantization of goods searches based on their embedding vectors and vectors of images. The proposed approach to the search for similar goods uses the DNN for features detection and embedding vectors, which are used for FAISS clustering. Methodology. The analytical and empirical methods of research based on the development and DNN are used, ML methods to determine features of goods and solve classification problems. Results. The architecture of the solution is based on the use of GCP services. Practical value. AI solutions have practical value for e-commerce, they help retain or return customers, and recommend products. As a result of the work, a basic solution to the problem of matching similar products based on the use of FAISS and Deep Learning algorithms in GCP was developed and tested.