Swiggy Uses 350+ Features and Multi-Task MLP to Predict Customer Lifetime Value

InfoQ (AI, ML & Data)
Read full post
Swiggy developed an in-house predicted lifetime value (pLTV) model using over 350 features and a multi-task multilayer perceptron to estimate new customers' long-term value before their first order. This model helps optimize advertising bids by predicting customer value despite sparse early data and skewed order distributions.

More in Machine Learning

Machine Learning4 min read

DeepSeek launches V4.1-Flash and retires V4-Pro, its flagship model

Covered by 2 sources
Machine Learning4 min read

Mistral wants open-weight AI to compete at the frontier. It just raised $3.5 billion to do it.

The New Stack (AI)
Machine Learning4 min read

Salesforce introduces Enterprise AI Harness, AI Control Plane

SiliconANGLE