Developed an AI-powered product search system for e-commerce websites.
Our project aims to imporve search query for e-commerce website by incoprating semantic search rather than relying on old school key word search method,Which improves customers retention time which grow online revenue, increases average order value and allows personilazatiion pipelined for specific customer's need. Even googles journey since the bought semantic database Freebase as the basis for the knowledge graph in 2010 to their introduction of MUM is quite remarkable.
Several industrial applications use embeddings. eg, Google search uses embeddings to match text and text to images, Snapchat uses them to serve the right ad to the right user at the right time and Meta uses them for their social search.
Main features of this project:
- Nice and beautiful interfacce.
- Retrieve results from a corpus of more than 30k products right now in just few milliseconds.
- You can also get semantic search results even more accurate than the original flipkart search engine.
- We used the original flipkart's product dataset and got more accurate and efficient results than flipkart.
- It stores the information and recommmend products based on what you have searched before or ordered.
- It also authenticates you with your email id and password.
This project was accomplished by our team:
Parth Madan (Machine learning enthusiast)
Pallav Sharma (Backend Developer)
Yash Agrawal (Machine learner and Frontend Developer)
Keshav Garg
Nitin Kumar Das