This document discusses using deep learning for customer churn prediction. Specifically, it proposes using unsupervised feature learning on abstract company-independent feature vectors to generate secondary features in a way that can be applied to any subscription-based company. This approach aims to eliminate the need for manual feature engineering by leveraging the ability of deep neural networks to learn secondary features in an unsupervised manner from raw data. The research was conducted by Framed Data in conjunction with the Data Science Institute at Lancaster University to develop a generalizable deep learning model for churn prediction that can be applied across different companies.

Deep Learning in Customer Churn Prediction: Unsupervised Feature Learning On Abstract Company Independent Feature Vectors PDF

The list of books you might like