Investigation on Customer Churn Prediction Using Machine Learning Techniques

Veningston, K; Rao, P. V. Venkateswara; Selvan, C; Ronalda, M.

doi:10.1007/978-981-16-5348-3_8

Cited by 5 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, in the banking industry, the credit card users can easily start to use another credit card. So, the only sign that the customer is churning is declining transactions (Veningston et al, 2022). On the other hand, in retail sector, it is not easy to see that signals.…”

Section: Customer Churnmentioning

confidence: 99%

Churn Customer Management in Retail Industry: A Case Study

Börühan

2022

İzmir İktisat Dergisi

View full text Add to dashboard Cite

Perakende sektörü, küresel olarak gelişmekte olan endüstriler arasında yer almakta, uygulayıcılar ve akademisyenler tarafından artan bir ilgi görmektedir. Perakende çevresi hızla değişmekte ve hem yerli hem de yabancı şirketlerden gelen büyük rekabet ile karakterize edilmektedir. Firmaların çoğu özdeş mallar üretmekte ve bunları rekabetçi fiyatlarla satmaya çalışmaktadır. Bu bağlamda yeni müşteriler bulmak ve onları sadık kılmak perakende sektörünün en zor işlerinden biridir. Firmalar için yeni müşteri bulmak eski müşteriyi elde tutmaktan beş kat daha pahalıya mal olmaktadır. Bu nedenle müşteriyi elde tutma kavramı akademik literatürde yeni bir terim olan “Kayıp Müşteri Yönetimi” nin ortaya çıkmasına neden olmuştur. Bu çalışmanın amacı, Perakendeci X'in İzmir'in farklı bölgelerinde bulunan düşük ve yüksek verimli mağazalarını veri zarflama analizi yaparak analiz etmek ve ardından bu mağazalardaki müşteri kaybının nedenlerini hem müşteriler hem de mağaza yöneticileri açısından incelemektir. Düşük ve yüksek verimli mağazaları bulmak için veri zarflama analizi yapmak üzere Perakendeci X'ten veriler toplanmıştır. Bir sonraki aşamada, her iki tarafın algılarını karşılaştırabilmek için hem mağaza yöneticileri hem de müşterilerle yarı yapılandırılmış görüşmeler yapılmıştır. Bu görüşmeler sonucunda müşteri kaybı nedenleri ürün ve stok düzeyi, fiyat, promosyonlar, fiziksel mağaza atmosferi, satış personelinin etkileşimi, satış sonrası hizmetler ve rakipler olmak üzere 7 grupta sınıflandırılmıştır.

show abstract

Section: Customer Churnmentioning

confidence: 99%

Churn Customer Management in Retail Industry: A Case Study

Börühan

2022

İzmir İktisat Dergisi

View full text Add to dashboard Cite

show abstract

“…Predictive algorithms on customer quitting can enable banks to identify the sensitive features that drive churn. A sensitivity analysis can enhance a bank's ability to know the customer closely and can alert a probable decision to churn [38]. Churn prediction is an integral part of customer relationship management.…”

Section: Need For Churn Prediction In the Industrymentioning

confidence: 99%

“…Telecommunication Artificial Neural Network [41] Deep Learning, Logistic Regression, and Naïve Bayes algorithms [45] Logistic Regressions, Linear Classifications, Naive Bayes, Decision Trees, Multilayer Perceptron Neural Networks, Support Vector Machines, and the Evolutionary Data Mining Algorithm [33] Linear regression, neural networks, decision trees, k-nearest neighbours, genetic algorithms, Naïve Bayes, Support Vector Machines (SVM), and Multilayer Perceptron Neural Networks [47] Decision Tree, Random Forest, Gradient Boosted Machine Tree "GBM", and Extreme Gradient Boosting "XGBOOST" [48] Random Forest [49] Long Short-term Memory (LSTM) and Convolutional Neural Networks (CNN) Models [50] Genetic Programming-based AdaBoost (GP-based AdaBoost) [51] Ensemble Learning with feature-grouping [52] Healthcare Stochastic Gradient Boosting Technique [53] Decision Trees, Naïve Bayes, and Neural Networks [54] Banking Artificial neural networks, decision trees, and class-weighted core support vector machines (CWC-SVM) and improved balanced random forests [35] Naïve Bayes model [38] Artificial Neural Networks (ANN) and Random Forests [44] Support Vector Machines [55] Retail Convolution Neural Networks and Restricted Boltzmann Machine [56] Insurance Randomized Trees Classifier and Gradient Boosting Model [57] Decision Tree (DT), Naïve Bayes (NB), and ANN. [58] IT Services Logistic regression, random forest, SVM, and Extreme Gradient Boosting (XGBoost), on three different domains.…”

Section: Industry Data Science Technique(s) Notable Contributorsmentioning

confidence: 99%

An Ensemble Model for Predicting Retail Banking Churn in the Youth Segment of Customers

Pramod

Raman

2022

Data

View full text Add to dashboard Cite

(1) This study aims to predict the youth customers’ defection in retail banking. The sample comprised 602 young adult bank customers. (2) The study applied Machine learning techniques, including ensembles, to predict the possibility of churn. (3) The absence of mobile banking, zero-interest personal loans, access to ATMs, and customer care and support were critical driving factors to churn. The ExtraTreeClassifier model resulted in an accuracy rate of 92%, and an AUC of 91.88% validated the findings. (4) Customer retention is one of the critical success factors for organizations so as to enhance the business value. It is imperative for banks to predict the drivers of churn among their young adult customers so as to create and deliver proactive enable quality services.

show abstract

An Efficient Customer Churn Prediction Technique Using Combined Machine Learning in Commercial Banks

2024

Oper. Res. Forum

View full text Add to dashboard Cite

Investigation on Customer Churn Prediction Using Machine Learning Techniques

Cited by 5 publications

References 11 publications

Churn Customer Management in Retail Industry: A Case Study

Churn Customer Management in Retail Industry: A Case Study

An Ensemble Model for Predicting Retail Banking Churn in the Youth Segment of Customers

An Efficient Customer Churn Prediction Technique Using Combined Machine Learning in Commercial Banks

Contact Info

Product

Resources

About