Calculating Customer Lifetime Value and Churn using Beta Geometric Negative Binomial and Gamma-Gamma Distribution in a NFT based setting

2025-01-02

AI Summary

Predicting customer lifetime value (CLV) and churn in NFT on-chain trading is challenging due to sparse user behavior, absence of explicit exit signals, and non-uniform, low-frequency transaction patterns. Method: This paper proposes the first CLV-churn joint modeling framework tailored for decentralized environments. It systematically adapts the classical BGNBD model—capturing purchase frequency and churn dynamics—and the Gamma-Gamma model—quantifying monetary value—to on-chain NFT data. We further design an NFT-specific RFM feature engineering pipeline and a robust parameter estimation procedure. Contribution/Results: The framework effectively addresses key on-chain data challenges, including irregularity, sparsity, and lack of natural termination points. Empirical evaluation across major NFT marketplaces demonstrates strong predictive performance: CLV prediction achieves MAE < 8.2%, while churn probability estimation attains AUC = 0.86. These results significantly support user segmentation and high-value customer retention strategies in decentralized applications.

Technology Category

• Machine Learning: Online Learning & Bandits
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Customer Lifetime Value (CLV) is an important metric that measures the total value a customer will bring to a business over their lifetime. The Beta Geometric Negative Binomial Distribution (BGNBD) and Gamma Gamma Distribution are two models that can be used to calculate CLV, taking into account both the frequency and value of customer transactions. This article explains the BGNBD and Gamma Gamma Distribution models, and how they can be used to calculate CLV for NFT (Non-Fungible Token) transaction data in a blockchain setting. By estimating the parameters of these models using historical transaction data, businesses can gain insights into the lifetime value of their customers and make data-driven decisions about marketing and customer retention strategies.

Problem

• NFT Transactions
• Customer Lifetime Value (CLV)
• Churn Prediction

Innovation

• Beta Geometric Negative Binomial Distribution (BGNBD)
• Gamma-Gamma Distribution
• Non-Fungible Token (NFT) CLV Prediction