Churn analysis using deep convolutional neural networks and autoencoders

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 labeled data of over 6 million customers using deep convolutional neural networks, which achieved an AUC of 0.743 on the test dataset using no more than 12 temporal features for each customer. Unsupervised learning was conducted using autoencoders to better understand the reasons for customer churn. Images that maximally activate the hidden units of an autoencoder trained with churned customers reveal ample opportunities for action to be taken to prevent churn among strong data, no voice users.

References in corpus (3)

• Improving neural networks by preventing co-adaptation of feature detectors
• ADADELTA: An Adaptive Learning Rate Method
• Theano: new features and speed improvements

Cited by in corpus (6)

• Customer Lifetime Value Prediction Using Embeddings
• Churn Prediction with Sequential Data and Deep Neural Networks. A Comparative Analysis
• Attending to Mathematical Language with Transformers
• A Recurrent Neural Network Survival Model: Predicting Web User Return Time
• Micro- and Macro-Level Churn Analysis of Large-Scale Mobile Games
• A Blended Deep Learning Approach for Predicting User Intended Actions