FinanceInfoQabout 3 hours ago
Swiggy Predicts Customer Value with 350+ Features
1 min read
Swiggy built an in-house predicted lifetime value model using over 350 pre-order features and a multi-task MLP for Food and Instamart. Adding order count as an auxiliary task cut model parameters by 63% while improving performance. The pLTV signal powers Google Target ROAS bidding for customer acquisition.
Level
Hype check
Tap to vote and see what everyone thinks.
