Evaluation of classification algorithms for banking customer’s behavior under Apache Spark Data Processing System

Etaiwi, Wael; Biltawi, Mariam; Naymat, Ghazi Al

doi:10.1016/j.procs.2017.08.280

Cited by 21 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various implementations of MapReduce were described by Goyal and Bharti (2015). Apache Spark (another engine for big data processing) was used to predict bank customer's behaviours (Etaiwi et al, 2017). Starfish is "a self-tuning system for big data analytics"; it was introduces by Herodotou et al (2011) to automatically provide a good performance.…”

Section: Discussion and Limitationsmentioning

confidence: 99%

Big and open linked data analytics ecosystem: Theoretical background and essential elements

Lněnička

Komárková

2019

Government Information Quarterly

View full text Add to dashboard Cite

Big and open linked data are often mentioned together because storing, processing, and publishing large amounts of these data play an increasingly important role in today's society. However, although this topic is described from the political, economic, and social points of view, a technical dimension, which is represented by big data analytics, is insufficient. The aim of this review article was to provide a theoretical background of big and open linked data analytics ecosystem and its essential elements. First, the key terms were introduced including related dimensions. Then, the key lifecycle phases were defined and involved stakeholders were identified. Finally, a conceptual framework was proposed. In contrast to previous research, the new ecosystem is formed by interactions of stakeholders in the following dimensions and their sub-dimensions: transparency, engagement, legal, technical, social, and economic. These relationships are characterized by the most important requisites and public policy choices affecting the data analytics ecosystem together with the key phases and activities of the data analytics lifecycle. The findings should contribute to relevant initiatives, strategies, and policies and their effective implementation.

show abstract

Section: Discussion and Limitationsmentioning

confidence: 99%

Big and open linked data analytics ecosystem: Theoretical background and essential elements

Lněnička

Komárková

2019

Government Information Quarterly

View full text Add to dashboard Cite

show abstract

“…In addition, to loss of revenue, the customer may not have already been covered by customers spending to date. Furthermore, it is always more difficult and expensive to acquire a new customer than it is to retain a current paying customer [4]. Churn prediction is a humongous business.…”

Section: Churn Predictionmentioning

confidence: 99%

Predicting customer churn using targeted proactive retention

Mishachandar¹,

Kumar²

2018

IJET

View full text Add to dashboard Cite

With the advent of innovative technologies and fierce competition, the choices for customers to choose from have increased tremendously in number. Especially in the case of a telecommunication industry, where deregulation is at its peak. Every year a new company springs up offering fitter options for its customers. This has turned the concentration of the business doers on churn prediction and business management models to sustain their places. Businesses approach churn in two ways, one is through targeted customer retention and through cause identification strategy. The literature of this paper provides a comprehensible understanding of the so far employed techniques in predicting customer churn. From that, it is quite evident that less attention has been given to the accuracy and the intuitiveness of churn models developed. Therefore, a novel approach of combining the models of Machine Learning and Big Data Analytics tools was proposed to deal churn prediction effectively. The purpose of this proposed work is to apply a novel retention technique called the targeted proactive retention to predict customer churning behavior in advance and help in their retention. This proposed work will help telecom companies to comprehend the risk associated with customer churn by predicting the possibility and the time of occurrence.

show abstract

“…Hybrid strategies have also been used for processing massive amount of customer information together with regression techniques that provide effective churn prediction results [ 22 ]. On the other hand, Etaiwi et al [ 23 ] showed that their Naïve Bayes model was able to beat a Support Vector Machine (SVM) model in terms of precision, recall, and F-measure.…”

Section: Introductionmentioning

confidence: 99%

A novel customer churn prediction model for the telecommunication industry using data transformation methods and feature selection

et al. 2022

View full text Add to dashboard Cite

Customer churn is one of the most critical issues faced by the telecommunication industry (TCI). Researchers and analysts leverage customer relationship management (CRM) data through the use of various machine learning models and data transformation methods to identify the customers who are likely to churn. While several studies have been conducted in the customer churn prediction (CCP) context in TCI, a review of performance of the various models stemming from these studies show a clear room for improvement. Therefore, to improve the accuracy of customer churn prediction in the telecommunication industry, we have investigated several machine learning models, as well as, data transformation methods. To optimize the prediction models, feature selection has been performed using univariate technique and the best hyperparameters have been selected using the grid search method. Subsequently, experiments have been conducted on several publicly available TCI datasets to assess the performance of our models in terms of the widely used evaluation metrics, such as AUC, precision, recall, and F-measure. Through a rigorous experimental study, we have demonstrated the benefit of applying data transformation methods as well as feature selection while training an optimized CCP model. Our proposed technique improved the prediction performance by up to 26.2% and 17% in terms of AUC and F-measure, respectively.

show abstract

Evaluation of classification algorithms for banking customer’s behavior under Apache Spark Data Processing System

Cited by 21 publications

References 13 publications

Big and open linked data analytics ecosystem: Theoretical background and essential elements

Big and open linked data analytics ecosystem: Theoretical background and essential elements

Predicting customer churn using targeted proactive retention

A novel customer churn prediction model for the telecommunication industry using data transformation methods and feature selection

Contact Info

Product

Resources

About