Billion-user Customer Lifetime Value Prediction: An Industrial-scale Solution from Kuaishou

TL;DR

This paper presents an industrial-scale solution for customer lifetime value prediction, introducing novel models and metrics that improve accuracy and are successfully deployed in real-world scenarios at Kuaishou.

Contribution

It proposes the ODMN framework with an innovative dependency modeling and a MDME module for better distribution handling, advancing LTV prediction methods.

Findings

ODMN improves model performance significantly.

MDME reduces modeling complexity and balances distributions.

Proposed metrics better evaluate distribution differences.

Abstract

Customer Life Time Value (LTV) is the expected total revenue that a single user can bring to a business. It is widely used in a variety of business scenarios to make operational decisions when acquiring new customers. Modeling LTV is a challenging problem, due to its complex and mutable data distribution. Existing approaches either directly learn from posterior feature distributions or leverage statistical models that make strong assumption on prior distributions, both of which fail to capture those mutable distributions. In this paper, we propose a complete set of industrial-level LTV modeling solutions. Specifically, we introduce an Order Dependency Monotonic Network (ODMN) that models the ordered dependencies between LTVs of different time spans, which greatly improves model performance. We further introduce a Multi Distribution Multi Experts (MDME) module based on the Divide-and-Conquer idea, which transforms the severely imbalanced distribution modeling problem into a series of relatively balanced sub-distribution modeling problems hence greatly reduces the modeling complexity. In addition, a novel evaluation metric Mutual Gini is introduced to better measure the distribution difference between the estimated value and the ground-truth label based on the Lorenz Curve. The ODMN framework has been successfully deployed in many business scenarios of Kuaishou, and achieved great performance. Extensive experiments on real-world industrial data demonstrate the superiority of the proposed methods compared to state-of-the-art baselines including ZILN and Two-Stage XGBoost models.