BriefGPT.xyz
Apr, 2016
使用深度卷积神经网络和自编码器进行流失分析
Churn analysis using deep convolutional neural networks and autoencoders
HTML
PDF
Artit Wangperawong, Cyrille Brun, Olav Laudy, Rujikorn Pavasuthipaisit
TL;DR
使用卷积神经网络对超过6百万个客户的行为数据进行图像化，以预测客户流失，并使用监督学习和无监督学习方法，通过最大化激活潜在单位来了解客户流失的原因，从而提出预防客户流失的解决方法。
Abstract
Customer temporal behavioral data was represented as images in order to perform churn prediction by leveraging
deep learning
architectures prominent in image classification.
supervised learning
was performed on l
→