Identifying Popular Products at An Early Stage for Apparel Industry
Date:
Supervisor: Professor Qingwei Jin Cooperating Company: Hangzhou Linezone Data
This research developed a novel approach to identify fast-selling apparel products early in the sales season.
Key Contributions
- Proposed AW Sales (Average Weekly Sales in Main Sales Period) as a new indicator to measure product popularity
- Developed novel features from weekly sales volume sequences
- Built a product popularity classification model using ranking algorithms
- Achieved 78.9% prediction accuracy, identifying fast-selling products 17 days earlier than traditional methods