Product Matching - Shopee National Data Science Competition 2020
Project Overview
Overview
Participated in the Shopee National Data Science Competition 2020 Advanced Category focused on large-scale product matching using machine learning and deep learning techniques.
Problem
The competition required participants to develop a model capable of determining whether two product listings represented the same or different products despite variations in text descriptions, images, and metadata.
Approach
Developed a Siamese Neural Network-based one-shot learning model for product similarity matching using paired product features to learn semantic relationships between product listings.
Key Results & Impact
- ✓Achieved Top 5% performance with Rank 6 out of 139 teams as a finalist in the Shopee National Data Science Competition 2020 under team “PelajarHsinchu”.
Technologies Used
Additional Information
Related Projects
Intelligent Sootblower
Optimization of Sootblower Operation Using Machine Learning for Reducing Sootblower Steam Consumption
Multi-task AI Model for Swimmer Tracking and Action Recognition
Design And Implementation Of A Lightweight Multi-task Deep Neural Network For Swimmer Action Recognition And Re-identification
Sensor-Based Human Action Recognition
A wearable AI action recognition system using smartphone and smartwatch sensors for real-time activity detection, sponsored by MOST Taiwan.