Out Of The Box Thinking: Improving Customer Lifetime Value Modelling Via Expert Routing And Game Whale Detection

By Shijie Zhang et al

Published on Oct. 21, 2023

Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction
2. Preliminary
3. Methodology
3.1 Overview of ExpLTV
3.2 Embedding Layer
3.3 Game Whale Detection
4. Summary

Summary

The document discusses the importance of Customer Lifetime Value (LTV) prediction in mobile game publishers and the impact of game whales on LTV models. It introduces ExpLTV, a novel framework that combines LTV prediction and game whale detection. The framework uses multi-task learning and a deep neural network-based game whale detector to improve accuracy. It addresses the challenges of existing LTV prediction models and proposes new strategies for short-term LTV prediction and game whale detection. Experimental results validate the effectiveness of ExpLTV in industrial datasets.