Earticle

초록

영어

This study evaluates the effectiveness of AI-driven CRM models in predicting consumer purchase behavior and examines how market volatility affects predictive performance. Using transactional data from Amazon, a customer-month panel is constructed to capture both active and inactive behavioral periods. Three modeling approaches are implemented, including a tree-based model and sequential learning models, to predict next-month purchase behavior using a time-based train-test split. The results demonstrate that LightGBM achieves superior predictive performance, with an AUC of 0.92, outperforming LSTM and GRU. However, the three models exhibit a decline in classification performance under high-volatility conditions. To further interpret model behavior, SHAP analysis is conducted, revealing that both behavioral features and market volatility significantly influence predictions. In particular, volatility emerges as an important contextual factor, with effects that vary across levels of customer activity.

목차

Abstract
Introduction
Literature review
Customer purchase behavior and CRM analytics
AI-driven CRM for customer purchase prediction
Market volatility and its implications for predictive modeling
Methods
Results
Conclusion
References

키워드

저자

• 르키아 [ 순천향대학교 경영학과 ]
• 최재원 [ 순천향대학교 경영학과 ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  한국경영정보학회 정기 학술대회 [KMIS Conference]

• 간기

  반년간

• 수록기간

  1990~2026

• 십진분류

  KDC 325 DDC 658