Bagging and Boosting Classification Trees to Predict Churn

Lemmens, Aurélie; Croux, Christophe

doi:10.1509/jmkr.43.2.276

Cited by 336 publications

(229 citation statements)

References 48 publications

Supporting

Mentioning

204

Contrasting

Unclassified

Order By: Relevance

“…It will be interesting to compare both approaches in future research. In the spirit of [27], a marketing study that finds bagging and boosting techniques to perform well for customer behavior prediction, and [1] who find Random Forests with SMOTE to perform best for purchase prediction in free-to-play games, we adopt tree-based (ensemble) methods combined with approaches to deal with the strong imbalance in the data [12]. We also include regression techniques as these have been reported to work well [15,17].…”

Section: Predicting Ltv In Non-contractual Freemium Settingsmentioning

confidence: 99%

Customer Lifetime Value Prediction in Non-Contractual Freemium Settings: Chasing High-Value Users Using Deep Neural Networks and SMOTE

Sifa¹,

Runge²,

Bauckhage³

et al. 2018

Proceedings of the 51st Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

In non-contractual freemium and sharing economy settings, a small share of users often drives the largest part of revenue for firms and co-finances the free provision of the product or service to a large number of users. Successfully retaining and upselling such high-value users can be crucial to firms' survival. Predictions of customers' Lifetime Value (LTV) are a much used tool to identify high-value users and inform marketing initiatives. This paper frames the related prediction problem and applies a number of common machine learning methods for the prediction of individual-level LTV. As only a small subset of users ever makes a purchase, data are highly imbalanced. The study therefore combines said methods with synthetic minority oversampling (SMOTE) in an attempt to achieve better prediction performance. Results indicate that data augmentation with SMOTE improves prediction performance for premium and high-value users, especially when used in combination with deep neural networks.

show abstract

Section: Predicting Ltv In Non-contractual Freemium Settingsmentioning

confidence: 99%

Customer Lifetime Value Prediction in Non-Contractual Freemium Settings: Chasing High-Value Users Using Deep Neural Networks and SMOTE

Sifa¹,

Runge²,

Bauckhage³

et al. 2018

Proceedings of the 51st Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…Churn is usually a rare event [30]. Many techniques have been proposed to deal with class imbalance in churn prediction [8,9]. In [31], the effect of class imbalance on a number of performance metrics is analyzed for probability estimation trees.…”

Section: Datamentioning

confidence: 99%

“…In this study, the use of ensemble learning for churn prediction is considered. Applications of ensemble classifiers to churn prediction include Random Forests [5], AdaBoost [6], AdaCost [7], Bagging [8], Stochastic Gradient Boosting [9], ensembles of Artificial Neural Networks [4] and the multi-classifier class-combiner technique [10]. These studies all demonstrate the beneficial impact of using ensemble classifiers over single classifiers for classification performance in the context of churn prediction.…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Ensembles of Probability Estimation Trees for Customer Churn Prediction

Bock

Poel

2010

Trends in Applied Intelligent Systems

View full text Add to dashboard Cite

Customer churn prediction is one of the most important elements of any Customer Relationship Management (CRM) strategy. In this study, a number of strategies are investigated to increase the lift of ensemble classification models. In order to increase lift performance, two elements of a number of well-known ensemble strategies are altered: (i) the potential of using probability estimation trees (PETs) instead of standard decision trees as base classifiers is investigated and (ii) a number of alternative fusion rules for the combination of ensemble member's outputs are proposed and compared. Experiments are conducted for four popular ensemble strategies (Bagging, the Random Subspace Method, SubBag and AdaBoost) on five real-life churn data sets. The results demonstrate the value of using PETs over standard decision trees in order to increase lift. Overall, the effect of the proposed strategies heavily depends on the chosen ensemble algorithm in which they are implemented.

show abstract

“…The individual predictions are combined via weighted voting. The popular combination methods of bagging [2] and boosting [6] are tested on a mixture of customer and contractual data in [8].…”

Section: Related Workmentioning

confidence: 99%

A Non-sequential Representation of Sequential Data for Churn Prediction

Eastwood

Gabrys

2009

Knowledge-Based and Intelligent Information and Engineering Systems

View full text Add to dashboard Cite

Abstract. We investigate the length of event sequence giving best predictions when using a continuous HMM approach to churn prediction from sequential data. Motivated by observations that predictions based on only the few most recent events seem to be the most accurate, a non-sequential dataset is constructed from customer event histories by averaging features of the last few events. A simple K-nearest neighbor algorithm on this dataset is found to give significantly improved performance. It is quite intuitive to think that most people will react only to events in the fairly recent past. Events related to telecommunications occurring months or years ago are unlikely to have a large impact on a customer's future behaviour, and these results bear this out. Methods that deal with sequential data also tend to be much more complex than those dealing with simple nontemporal data, giving an added benefit to expressing the recent information in a non-sequential manner.

show abstract

Bagging and Boosting Classification Trees to Predict Churn

Cited by 336 publications

References 48 publications

Customer Lifetime Value Prediction in Non-Contractual Freemium Settings: Chasing High-Value Users Using Deep Neural Networks and SMOTE

Customer Lifetime Value Prediction in Non-Contractual Freemium Settings: Chasing High-Value Users Using Deep Neural Networks and SMOTE

Ensembles of Probability Estimation Trees for Customer Churn Prediction

A Non-sequential Representation of Sequential Data for Churn Prediction

Contact Info

Product

Resources

About