An effective hybrid learning system for telecommunication churn prediction

Customer churn has emerged as a critical issue for Customer Relationship Management and customer retention in the telecommunications industry, thus churn prediction is necessary and valuable to retain the customers and reduce the losses. Moreover, high predictive accuracy and good interpretability of the results are two key measures of a classification model. More studies have shown that single model-based classification methods may not be good enough to achieve a satisfactory result. To obtain more accurate predictive results, we present a novel hybrid model-based learning system, which integrates the supervised and unsupervised techniques for predicting customer behaviour. The system combines a modified k-means clustering algorithm and a classic rule inductive technique (FOIL).Three sets of experiments were carried out on telecom datasets. One set of the experiments is for verifying that the weighted k-means clustering can lead to a better data partitioning results; the second set of experiments is for evaluating the classification results, and comparing it to other well-known modelling techniques; the last set of experiment compares the proposed hybrid-model system with several other recently proposed hybrid classification approaches. We also performed a comparative study on a set of benchmarks obtained from the UCI repository. All the results show that the hybrid model-based learning system is very promising and outperform the existing models.     

Churn prediction using comprehensible support vector machine: An analytical CRM application

Support vector machine (SVM) is currently state-of-the-art for classification tasks due to its ability to model nonlinearities. However, the main drawback of SVM is that it generates “black box” model, i.e. it does not reveal the knowledge learnt during training in human comprehensible form. The process of converting such opaque models into a transparent model is often regarded as rule extraction. In this paper we proposed a hybrid approach for extracting rules from SVM for customer relationship management (CRM) purposes. The proposed hybrid approach consists of three phases. (i) During first phase; SVM-RFE (SVM-recursive feature elimination) is employed to reduce the feature set. (ii) Dataset with reduced features is then used in the second phase to obtain SVM model and support vectors are extracted. (iii) Rules are then generated using Naive Bayes Tree (NBTree) in the final phase. The dataset analyzed in this research study is about Churn prediction in bank credit card customer (Business Intelligence Cup 2004) and it is highly unbalanced with 93.24% loyal and 6.76% churned customers. Further we employed various standard balancing approaches to balance the data and extracted rules. It is observed from the empirical results that the proposed hybrid outperformed all other techniques tested. As the reduced feature dataset is used, it is also observed that the proposed approach extracts smaller length rules, thereby improving the comprehensibility of the system. The generated rules act as an early warning expert system to the bank management.     

数据挖掘在客户流失管理中的应用

客户流失是通信行业的难题。阐述了数据挖掘技术的数据分析、信息处理和预测功能,并举例介绍了数据挖掘在客户流失管理中的应用。     

Experimental study of the slug/churn flow transition in a single Taylor bubble

A study is presented of the hydrodynamic behaviour of very long gas slugs, rising co-currently with water along a 20 mm i.d. vertical tube. Visual observation (supported by pictures from video and still cameras) and the signals from a set of three fast response differential pressure transducers, were used to elucidate the flow behaviour of individual slugs of argon, with densities in the range 6.6-21.5 kg/m³ (corresponding to operating pressures in the range 0.4-1.3 MPa), as they rose in water that moved up the tube, with constant average velocity in the range 0.17-1.4 m/s. For the lower gas densities and liquid velocities the slugs were stable, but for the higher liquid velocities and/or gas densities, the slugs would become unstable, as a result of flooding in the wetted wall flow around them. The video sequences show clearly that, at the higher pressures, liquid from the film was dragged up by the gas, while the still pictures document the corresponding transition to churn flow in the lower regions of the rising slugs.     

对等网络Churn问题评估模型与分析

提出一个Churn问题评估模型，以及基于该模型的2种比较模式和一个公式化描述。使用模型对3种常用对等网络分析得出以下重要结论：Chord算法在Churn环境下性能最优，影响Churn问题众多因素中最重要的是节点平均生存时间，Churn带来的两类影响不可能同时有效解决，二者存在平衡制约关系。评估模型和相关结论可为Churn环境下研究现有对等网络和设计新对等网协议提供分析平台。     

SVM在移动通信客户流失预测中的应用研究

使用支持向量机(SVM,Support Vector Machine)数据挖掘方法对移动通信行业客户流失倾向进行预测,对支持向量机同决策树算法预测的结果进行对比,结果表明支持向量机对本文所选取的属性数据具有更强的分类能力,而且在不同训练数据规模情况下预测模型有较好的稳定性。实验证实,运用本研究模型选取全体客户的22.31%,可以预测出50.07%流失的客户,表明本研究中提出的预测模型具有实际应用价值。     

Mining churning behaviors and developing retention strategies based on a partial least squares (PLS) model

In a very competitive mobile telecommunication business environment, marketing managers need a business intelligence model that allows them to maintain an optimal (at least a near optimal) level of churners very effectively and efficiently while minimizing the costs throughout their marketing programs. As a first step toward optimal churn management program for marketing managers, this paper focuses on building an accurate and concise predictive model for the purpose of churn prediction utilizing a partial least squares (PLS)-based methodology on highly correlated data sets among variables. A preliminary experiment demonstrates that the presented model provides more accurate performance than traditional prediction models and identifies key variables to better understand churning behaviors. Further, a set of simple churn marketing programs—device management, overage management, and complaint management strategies—is presented and discussed.     

深度随机森林在离网预测中的应用

在电信运营商领域,离网预测模型是企业决策者用来发现潜在离网用户(即停用运营商服务)的主要手段。目前离网预测模型都是基于逻辑回归、决策树、神经网络及随机森林等浅层机器学习算法,但是在大数据的背景下,这些浅层算法在预测问题上很难取得更高的精度。因此,提出了一种新型的深层结构模型——深度随机森林,通过将传统浅层随机森林堆积成深层结构模型,获得更高的预测精度。在运营商真实数据上进行了大量实验,结果证明深层随机森林模型比传统浅层机器学习算法在离网预测问题上可以得到更好的效果。同时,增大训练数据量可以进一步提升深层随机森林的预测能力,从而证明了在大数据环境下深层模型的潜力。     

基于数据挖掘的移动通信业客户流失预警系统设计

借助SASEM平台。对移动通信业务数据使用数据挖掘算法建立客户细分模型,能够刻画移动通信客户的行为特征,并以此建立客户流失预测模型。从而建立一个移动通信业客户流失预警系统。实践证明,该方法实用、可操作性强,对支持企业客户关系管理产生了积极的影响。     

Improved churn prediction in telecommunication industry using data mining techniques

To survive in today's telecommunication business it is imperative to distinguish customers who are not reluctant to move toward a competitor. Therefore, customer churn prediction has become an essential issue in telecommunication business. In such competitive business a reliable customer predictor will be regarded priceless. This paper has employed data mining classification techniques including Decision Tree, Artificial Neural Networks, K-Nearest Neighbors, and Support Vector Machine so as to compare their performances. Using the data of an Iranian mobile company, not only were these techniques experienced and compared to one another, but also we have drawn a parallel between some different prominent data mining software. Analyzing the techniques’ behavior and coming to know their specialties, we proposed a hybrid methodology which made considerable improvements to the value of some of the evaluations metrics. The proposed methodology results showed that above 95% accuracy for Recall and Precision is easily achievable. Apart from that a new methodology for extracting influential features in dataset was introduced and experienced.