• Corpus ID: 21800665

Predicting user churn on streaming services using recurrent neural networks

@inproceedings{Martins2017PredictingUC,
  title={Predicting user churn on streaming services using recurrent neural networks},
  author={Helder Martins},
  year={2017}
}
Providers of online services have witnessed a rapid growth of their user base in the last few years. The phenomenon has attracted an increasing number of competitors determined on obtaining their o ... 
ChOracle: A Unified Statistical Framework for Churn Prediction
TLDR
ChOracle is introduced, an oracle that predicts the user churn by modeling the user return times to service by utilizing a combination of Temporal Point Processes and Recurrent Neural Networks and incorporates latent variables into the proposed recurrent neural network to model the latent user loyalty to the system.
Non-Contractual Churn Prediction with Limited User Information
TLDR
The study found that the best LSTM models did outperform the other methods in terms of precision, recall, F -measure and AUC – but not accuracy, so further research is advised.
Churn Prediction with Sequential Data and Deep Neural Networks. A Comparative Analysis
TLDR
This paper assesses the performance of neural networks for churn modeling using recency, frequency, and monetary value data from a financial services provider and shows that RFM variables in combination with LSTM neural networks have larger top-decile lift and expected maximum profit metrics than regularized logistic regression models with commonly-used demographic variables.
Customer Churn Prediction Model Based on LSTM and CNN in Music Streaming
TLDR
A model based on L STM and CNN which has cross-layer connections between the LSTM layers and the convolution layers which can simultaneously learn latent sequential information and capture important local features from time series features is proposed.
Churning while Learning: Maximizing User Engagement in a Recommendation System
TLDR
A two-period model for the platform recommendation problem is proposed and it is found that accounting for heterogeneous churning behavior while learning the efficacy of new content can lead to improvements of up to 14% in the long-term user engagement.
A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Games
  • Xi Liu, Muhe Xie, Na Wang
  • Computer Science
    2018 IEEE International Conference on Data Mining (ICDM)
  • 2018
TLDR
This paper devise a novel semi-supervised and inductive embedding model that jointly learns the prediction function and the embedding function for user-app relationships and designs a novel attributed random walk technique that takes into consideration both topological adjacency and attribute similarities.
Micro- and macro-level churn analysis of large-scale mobile games
TLDR
This paper proposes a novel semi-supervised and inductive embedding model that jointly learns the prediction function and the embedding function for user–app relationships and designs a novel attributed random walk technique that takes into consideration both topological adjacency and attribute similarities.
Lifelog Data-Based Prediction Model of Digital Health Care App Customer Churn: Retrospective Observational Study
TLDR
The model with a recurrent neural network architecture that used log data and message data demonstrated high performance for churn classification and is expected to help identify signs of user churn in advance and improve the adherence in digital health care.

References

SHOWING 1-10 OF 68 REFERENCES
Behavioral Modeling for Churn Prediction: Early Indicators and Accurate Predictors of Custom Defection and Loyalty
TLDR
This paper presents a unified analytic framework for detecting the early warning signs of churn, and assigning a "Churn Score" to each customer that indicates the likelihood that the particular individual will churn within a predefined amount of time.
Customer Churn in Mobile Markets A Comparison of Techniques
TLDR
The paper proves the superiority of decision tree technique and stresses the needs for more advanced methods to churn modelling by empirically comparing two techniques: Customer churn - decision tree and logistic regression models.
A Customer Churn Prediction Model in Telecom Industry Using Boosting
TLDR
Experimental evaluation reveals that boosting also provides a good separation of churn data; thus, boosting is suggested for churn prediction analysis.
The Netflix Prize
Netflix released a dataset containing 100 million anonymous movie ratings and challenged the data mining, machine learning and computer science communities to develop systems that could beat the
Review of Data Mining Techniques for Churn Prediction in Telecom
TLDR
This paper provides a review of around 100 recent journal articles starting from year 2000 to present the various data mining techniques used in multiple customer based churn models, thereby providing a roadmap to new researchers to build upon novel churn management models.
Churn analysis using deep convolutional neural networks and autoencoders
TLDR
Customer temporal behavioral data was represented as images in order to perform churn prediction by leveragingDeep convolutional neural networks prominent in image classification to better understand the reasons for customer churn.
...
...