# Churn prediction in online gambling

arXiv: https://arxiv.org/abs/2201.02463 · HTML: https://mlsanity.com/paper/2201.02463/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 22 references that are in the map.
- First posted on arXiv 7 Jan 2022.

## Builds on (most cited first, 5 of 5)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [Introducing Neuromodulation in Deep Neural Networks to Learn Adaptive Behaviours](https://mlsanity.com/paper/1812.09113/) (2018)
- [A bio-inspired bistable recurrent cell allows for long-lasting memory](https://mlsanity.com/paper/2006.05252/) (2020)

## Built on by (most cited first, 2 of 2)

- [User Engagement in Mobile Health Applications](https://mlsanity.com/paper/2206.08178/) (2022)
- [Challenges and opportunities in applying Neural Temporal Point Processes to large scale industry data](https://mlsanity.com/paper/2208.08623/) (2022)

## Abstract (arXiv)

In business retention, churn prevention has always been a major concern. This work contributes to this domain by formalizing the problem of churn prediction in the context of online gambling as a binary classification task. We also propose an algorithmic answer to this problem based on recurrent neural network. This algorithm is tested with online gambling data that have the form of time series, which can be efficiently processed by recurrent neural networks. To evaluate the performances of the trained models, standard machine learning metrics were used, such as accuracy, precision and recall. For this problem in particular, the conducted experiments allowed to assess that the choice of a specific architecture depends on the metric which is given the greatest importance. Architectures using nBRC favour precision, those using LSTM give better recall, while GRU-based architectures allow a higher accuracy and balance two other metrics. Moreover, further experiments showed that using only the more recent time-series histories to train the networks decreases the quality of the results. We also study the performances of models learned at a specific instant t, at other times tprime > t. The results show that the performances of the models learned at time t remain good at the following instants tprime > t, suggesting that there is no need to refresh the models at a high rate. However, the performances of the models were subject to noticeable variance due to one-off events impacting the data.