aiqbench takeMachine Learning

Swiggy's implementation of a multi-task multi-layer perceptron (MLP) demonstrates how auxiliary prediction tasks can significantly reduce model complexity while enhancing performance in cold-start scenarios. By integrating order count as an additional task, the system achieved a 63% reduction in parameters without sacrificing accuracy, offering a practical approach to optimizing customer acquisition signals for food and quick commerce platforms.

Sources coveringInfoQ, The Verge

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

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

InfoQSeptember 2, 20263 min read

Swiggy developed an in-house predicted lifetime value model using more than 350 pre order features and a multi task MLP for Food and Instamart. Adding order count as an auxiliary task reduced model parameters by 63% while improving predictive performance. The pLTV signal is used with Google Target ROAS bidding to optimize customer acquisition. By Leela Kumili

Swiggy has developed an in-house predicted lifetime value (pLTV) model to estimate the long-term value of new customers across its food delivery and Instamart quick commerce businesses. The model is designed to generate a useful signal before a customer's first order, allowing Swiggy to use predicted value in advertising bid optimization…

Excerpt shown under the publisher's RSS terms · 51 words · full text and figures are on the publisher's site

Read at InfoQ ↗Ask about this article