用雷达图序列捕捉用户行为变化，提前预测零订阅平台的流失风险。
RadarSeq: A Temporal Vision Framework for User Churn Prediction via Radar Chart Sequences
- 将用户每日行为转为雷达图序列，结合CNN与双向LSTM建模时空特征。
- 在真实数据上实现F1提升17.7、精确率提升29.4、AUC提升16.1。
- 适合需要可解释性与高效部署的动态共享经济平台用户留存分析。
在无订阅制的零工经济平台中，用户流失表现为隐式失联，缺乏明确标签且行为动态变化，给预测带来挑战。现有方法多依赖聚合快照或静态可视化，难以捕捉关键的时间线索。本文提出一种时序感知的计算机视觉框架，将用户行为模式建模为一系列雷达图图像，每张图编码日级行为特征。通过融合预训练CNN编码器与双向LSTM，该架构同时捕捉空间结构与时间演变规律。在大规模真实数据集上的实验表明，该方法显著优于经典模型及基于ViT的雷达图基线，分别在F1分数上提升17.7，精确率提升29.4，AUC提升16.1，并具备更强可解释性。其模块化设计、可解释性工具和高效部署特性，使其适用于动态零工平台的大规模流失预测。
原文摘要 · Abstract (English)
Predicting user churn in non-subscription gig platforms, where disengagement is implicit, poses unique challenges due to the absence of explicit labels and the dynamic nature of user behavior. Existing methods often rely on aggregated snapshots or static visual representations, which obscure temporal cues critical for early detection. In this work, we propose a temporally-aware computer vision framework that models user behavioral patterns as a sequence of radar chart images, each encoding day-level behavioral features. By integrating a pretrained CNN encoder with a bidirectional LSTM, our architecture captures both spatial and temporal patterns underlying churn behavior. Extensive experiments on a large real-world dataset demonstrate that our method outperforms classical models and ViT-based radar chart baselines, yielding gains of 17.7 in F1 score, 29.4 in precision, and 16.1 in AUC, along with improved interpretability. The framework's modular design, explainability tools, and efficient deployment characteristics make it suitable for large-scale churn modeling in dynamic gig-economy platforms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。