Customer Lifetime Value Prediction with Uncertainty Estimation Using Monte Carlo Dropout
This work solves the problem of uncertainty-aware LTV prediction for companies, particularly in mobile gaming, to optimize revenue strategies, though it is incremental as it builds on existing neural network methods by adding Monte Carlo Dropout.
The paper tackled the problem of predicting customer lifetime value (LTV) by addressing the lack of uncertainty estimation in traditional deep learning models, resulting in a substantial improvement in predictive accuracy, specifically in Top 5% Mean Absolute Percentage Error, compared to state-of-the-art methods.
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.