Customer Lifetime Value Prediction with Uncertainty Estimation Using Monte Carlo Dropout

TL;DR

This work proposes a novel approach that enhances the architecture of purely neural network models by incorporating the Monte Carlo Dropout (MCD) framework, and provides confidence metric as an extra dimension for performance evaluation across various neural network models, facilitating more informed business decisions.

Abstract

Accurately predicting customer Lifetime Value (LTV) is crucial for companies to optimize their revenue strategies. Traditional deep learning models for LTV prediction are effective but typically provide only point estimates and fail to capture model uncertainty in modeling user behaviors. To address this limitation, we propose a novel approach that enhances the architecture of purely neural network models by incorporating the Monte Carlo Dropout (MCD) framework. We benchmarked the proposed method using data from one of the most downloaded mobile games in the world, and demonstrated a substantial improvement in predictive Top 5\% Mean Absolute Percentage Error compared to existing state-of-the-art methods. Additionally, our approach provides confidence metric as an extra dimension for performance evaluation across various neural network models, facilitating more informed business decisions.

Figures (2)

• Figure 1: Model accuracy across different confidence intervals
• Figure 2: Major metrics using different MCD trials. Both the normalized Gini coefficient and MAPE improved as the number of trials increased.