Enhancing Customer Churn Prediction in Digital Banking using Ensemble Modeling

In today’s competitive banking environment, Customer Relationship Management (CRM) has become essential for nationalised banks striving to enhance customer satisfaction and loyalty, especially in urban areas like Coimbatore City. This study aims to explore recent trends in CRM practices within nationalised banks, with a focus on assessing their effectiveness in improving customer service utilization and satisfaction. The problem addressed is the need for nationalised banks to adapt CRM strategies that meet customer expectations and maintain loyalty amid growing competition from private and digital banks. The research objectives are to analyze the effectiveness of CRM strategies in enhancing service utilization and to assess their impact on customer satisfaction in Coimbatore. A Descriptive Research Design was employed, and data was collected from a sample of 134 respondents using Convenience Sampling. The study uses statistical tools such as ANOVA, Correlation Analysis, and Multiple Linear Regression to examine relationships among CRM strategies, service utilization, and customer satisfaction. Key findings reveal that digital banking tools, personalization, and user-friendly interfaces are highly valued by younger customers. Moreover, locality and educational level significantly influence CRM effectiveness, highlighting the need for location-specific strategies. Recommendations include enhancing digital banking platforms, expanding ATM networks, and investing in customer service training to improve conflict resolution. In conclusion, effective CRM strategies are essential for boosting customer satisfaction and fostering loyalty, underscoring the importance of continual adaptation and innovation in nationalised banks’ CRM practices to meet evolving customer needs in Coimbatore City.

The classification model in machine learning has been employed to address different problems. Machine Learning classification is an effective method to realize customer churn prediction. This article provides a comparative study of machine learning from the perspective of predicting customer churn. Customer churn is one of the obstacles hindering the development of companies. Through classification approaches based on machine learning, customer churn can be predicted precisely, thus providing decision-making capabilities to these companies. Customer churn prediction is a typical classification problem and can be addressed by the use of a decision tree or random forest model. In this paper, decision tree and random forest models are employed to predict customer churn, using sales data provided by a chemical company from 2012 to 2020. We analyze the underlying risk of customer churn and the customer churn factors, including the low-priced count (LC), total amount of money (TM), and creation time (CT). The prediction results of the two models are evaluated by calculating various metrics. The experimental results indicate that the low-priced count (LC) is the most essential factor for customer churn. The results of the comparison, considering the training error and generalization error including: confusion matrix, ROC curve, AUC, precision, recall, and F1 score, reveal that the random forest model has better prediction accuracy than the decision tree model.

Purpose: The banking industry is one of the service industries that contributes to national income and serves as an intermediary institution to accommodate public funds and channel them back to productive economic activities. This study will look into the factors that influence customers' intentions to use digital banking and utilize it to their advantages and future advancements. This research uses TAM (technology acceptance model) as framework to explain the intention to adopt digital banking phenomenon. In addition to TAM components of perceived ease of use and perceived usefulness, this research also put perceived risk, trust, and inconvenience into the TAM framework. 
 Design/methodology/approach: This study using quantitative descriptive research design with conclusive research. This study use non-probability sampling with judgmental technique to 140 respondents that meet the research sampling criteria. IBM SPSS version 24 is used for multiple regression data processing and analysis.
 Findings: The findings show that perception ease of using, perceived usefulness, and perceived risk have no effect on intention to use digit banking. Furthermore, the findings confirm the positive influence of trust and convenience on the intention of using digital banking.
 Research limitations/implications: The study used Google Forms, which limited respondents' time to answer, and respondents' opinions may be prejudiced. This study's sample size reduced respondents' general representation, and the results were limited to one country. Future academics may add others variables that affect digital banking adoption into the framework. The researchers also recommend bigger sample sizes with a more diverse demographic profile of respondents.
 Practical implications: Digital banks might emphasize trust and convenience to attract new consumers. Delivering on promises will build trust in services. Digital bank providers can also emphasize their technology's convenience, which allows clients to do financial transactions anywhere and anytime.
 Originality/value: This study will serve as a reference for digital bank providers in promoting the usage of digital bank services in order to accelerate Indonesian digital bank adoption, which is still lagging behind that of other Asian countries.
 Paper type: Research paper

Customer churn is a critical concern for the telecommunication industry. Understanding and predicting customer churn can lead to more effective retention strategies and an increase in profitability. Predicting customer churn allows telecommunication companies to identify potentially dissatisfied customers early on and take proactive measures to retain them. Due to a large client base, the telecom industry generates a large volume of data on a daily basis. Decision makers and business analysts stressed that acquiring new customers is more expensive than retaining existing ones. Business analysts and customer relationship management (CRM) analysts must understand the reasons for customer churn as well as behaviour patterns from existing churn data. This paper proposes a churn prediction model that uses classication and clustering techniques to identify churn customers and provides the factors that contribute to customer churning in the telecom sector. The results presented shows that XBoost and Random Forest achieved higher prediction accuracy when compared to K- Nearest Neighbours, Support Vector Machines and Decision Trees in terms of accuracy, precision, F1-Score and recall.

There is a growing tendency for more companies to develop towards a subscription business model. Under such a trend, it is important to learn about the customer churn rate within the business, learn from it and adjust business strategies accordingly. This paper aims to predict customer churn rate in subscription business models using a variety of machine learning algorithms. Through comparing the results from the different algorithms, the best algorithms can be identified so that it provides an insight on which algorithm a subscription business should choose in order to predict customer churn most effectively. In this work, a total of 21 features and 9 algorithms are taken into account. Through a set of rigorous procedure including data preparation, feature engineering, feature selection, model building, and finally, model evaluation, three algorithms, namely Logistic Regression, Gradient Boosting (SMOTE) and Neural Network outperformed other 6 algorithms. The best performing algorithm being Logistic Regression with its 79.6% prediction accuracy, thus the conclusion that when subscription business predicts customer churn rate, Logistic Regression is the most preferable algorithm. During the process of feature engineering, SMOTE did not improve the model performance as it supposed to, so it is not recommended during the model building process.

The emergence of digital banks in Indonesia, such as Blu by BCA, Bank Jago, Allo Bank, and Bank Neo Commerce has been driven by the positive response from the public and the increasing demand for digital banking services, especially in the Covid-19 pandemic. With the growth of digital banking in Indonesia, it is important to understand the factors that shape customer satisfaction and loyalty. This study aims to examine the influence of customer experience on satisfaction and loyalty in the digital banking industry, with focus in Indonesia (Makassar). Seven hypotheses are proposed to examine these relationships. The study utilizes a sample of digital banking customers through convenience sampling and collects data using electronic questionnaires. Structural equation modelling (PLS) is employed for data analysis, considering validity and reliability measures. The findings reveal that convenience and security significantly influence customer satisfaction, while the influence of usefulness is not supported. Additionally, customer satisfaction is identified as a significant mediator in the relationship between customer experience and loyalty. This study emphasizes the importance of improving convenience and security aspects in digital banking services to enhance customer satisfaction and loyalty. In conclusion, this research provides valuable insights for digital banks in Makassar, Indonesia, to enhance their services and cultivate strong customer relationships. Prioritizing convenience and security, along with understanding the influence of customer satisfaction on loyalty, can drive the success of digital banking firm.

This study aims to analyze the effect of service quality and Fear of Missing Out (FOMO) on public interest in using digital banks in Indonesia, with trust as a moderating variable. With the increasing digitalization in the banking sector, understanding the factors that drive public interest in digital banking has become crucial, particularly amid concerns over service security and reliability. This study employs a quantitative approach with a survey method involving 464 respondents, both users and non-users of digital banking services across Indonesia. Data analysis was conducted using the Partial Least Square - Structural Equation Modeling (PLS-SEM) method with the assistance of SmartPLS software version 4.1.0.2. Service quality was measured using indicators such as reliability, accessibility, responsiveness, and service personalization. Meanwhile, FOMO was measured through indicators such as the perception of missing out, social anxiety, drive to adopt new technology, and social media influence. The results show that service quality has no significant effect on digital banking interest. However, FOMO has a significant positive effect on public interest in using these services. Additionally, trust has a significant but negative moderating effect on the relationship between FOMO and usage interest. This means that as trust in digital banking increases, the influence of FOMO on interest tends to decrease. This suggests that users who already trust the security of digital banking make more rational decisions and are less influenced by trends or social pressure. On the other hand, trust does not moderate the relationship between service quality and digital banking interest.

This Study Investigates The Factors That Influence Users' Intention To Continue Using Digital Banking Services In Indonesia, Focusing On Fully Digital Banks Without Branches Such As Blu By Bca Digital, Jenius, Seabank And Others. Based On The Technology Continuance Theory (Tct), This Study Integrates The Main Constructs Of The Technology Acceptance Model (Tam) And The Expectation Confirmation Model (Ecm) And Extends The Framework By Including Two Important Factors In The Context Of Digital Finance, Namely Trust And Perceived Risk. Data Were Collected Through A Structured Online Questionnaire, Resulting In 227 Valid Responses From Active Digital Banking Users. Partial Least Squares Structural Equation Modeling (Pls-Sem) Was Employed To Test Eight Hypotheses Involving Confirmation, Perceived Ease Of Use, Perceived Usefulness, Satisfaction, Attitude Toward The Service, Trust And Perceived Risk. The Results Revealed That Confirmation And Perceived Ease Of Use Significantly Influenced Perceived Usefulness, Which In Turn Had A Strong Impact On User Satisfaction. Furthermore, Satisfaction Improved User Attitudes Toward The Service. However, The Direct Effects Of Satisfaction, Attitude, Trust, And Perceived Risk On Continuance Intention Were Found To Be Statistically Insignificant, Indicating Potential Indirect Pathways Or Conceptual Overlap. Discriminant Validity Issues Identified Through Htmt Analysis Indicated High Intercorrelations Among These Constructs, Warranting Further Refinement In Future Models. This Study Contributes To The Post-Adoption Literature By Validating An Extended Tct Model In The Context Of Indonesian Digital Banking. It Offers Practical Recommendations For Digital Banks To Focus On Functional Value And User Experience Rather Than Solely Emphasizing Trust-Building Or Risk Reduction. Future Research Should Address The Model’s Limitations By Including Moderating Variables, Using Longitudinal Data And Expanding To Cross-National Contexts.

The development of information technology has transformed the landscape of banking services, leading to the emergence of digital banks as a promising alternative. Digital banks offer banking services without physical presence, relying on digital platforms for all transactions and communications. However, with rapid growth, digital banks face various challenges, including stringent regulations, increased competition, and effective risk management. This study aims to analyze the financial health of digital banks in Indonesia during the period 2019-2022, focusing on six digital banks listed on the Indonesia Stock Exchange. The RGEC method is used to evaluate key aspects such as risk profile, corporate governance, earnings, and capital. The results of the analysis show variations in the financial performance of digital banks, with some banks showing consistent growth while others experiencing fluctuations. However, overall, digital banks demonstrate relatively healthy performance in managing risks and maintaining capital adequacy. By understanding the factors influencing the financial health of digital banks, this study provides valuable insights for investors, regulators, and other stakeholders in understanding the dynamics of the digital banking industry in Indonesia.

Improving the diagnosis and prediction of customer churn: A heterogeneous hazard modeling approach

To predict the potential geographic distribution of Oncomelania hupensis in Yunnan Province using random forest (RF) and maximum entropy (MaxEnt) models, so as to provide insights into O. hupensis surveillance and control in Yunnan Province. The O. hupensis snail survey data in Yunnan Province from 2015 to 2016 were collected and converted into O. hupensis snail distribution site data. Data of 22 environmental variables in Yunnan Province were collected, including twelve climate variables (annual potential evapotranspiration, annual mean ground surface temperature, annual precipitation, annual mean air pressure, annual mean relative humidity, annual sunshine duration, annual mean air temperature, annual mean wind speed, ≥ 0 ℃ annual accumulated temperature, ≥ 10 ℃ annual accumulated temperature, aridity and index of moisture), eight geographical variables (normalized difference vegetation index, landform type, land use type, altitude, soil type, soil textureclay content, soil texture-sand content and soil texture-silt content) and two population and economic variables (gross domestic product and population). Variables were screened with Pearson correlation test and variance inflation factor (VIF) test. The RF and MaxEnt models and the ensemble model were created using the biomod2 package of the software R 4.2.1, and the potential distribution of O. hupensis snails after 2016 was predicted in Yunnan Province. The predictive effects of models were evaluated through cross-validation and independent tests, and the area under the receiver operating characteristic curve (AUC), true skill statistics (TSS) and Kappa statistics were used for model evaluation. In addition, the importance of environmental variables was analyzed, the contribution of environmental variables output by the models with AUC values of > 0.950 and TSS values of > 0.850 were selected for normalization processing, and the importance percentage of environmental variables was obtained to analyze the importance of environmental variables. Data of 148 O. hupensis snail distribution sites and 15 environmental variables were included in training sets of RF and MaxEnt models, and both RF and MaxEnt models had high predictive performance, with both mean AUC values of > 0.900 and all mean TSS values and Kappa values of > 0.800, and significant differences in the AUC (t = 19.862, P < 0.05), TSS (t = 10.140, P < 0.05) and Kappa values (t = 10.237, P < 0.05) between two models. The AUC, TSS and Kappa values of the ensemble model were 0.996, 0.954 and 0.920, respectively. Independent data verification showed that the AUC, TSS and Kappa values of the RF model and the ensemble model were all 1, which still showed high performance in unknown data modeling, and the MaxEnt model showed poor performance, with TSS and Kappa values of 0 for 24%(24/100) of the modeling results. The modeling results of 79 RF models, 38 MaxEnt models and their ensemble models with AUC values of > 0.950 and TSS values of > 0.850 were included in the evaluation of importance of environmental variables. The importance of annual sunshine duration (SSD) was 32.989%, 37.847% and 46.315% in the RF model, the MaxEnt model and their ensemble model, while the importance of annual mean relative humidity (RHU) was 30.947%, 15.921% and 28.121%, respectively. Important environment variables were concentrated in modeling results of the RF model, dispersed in modeling results of the MaxEnt model, and most concentrated in modeling results of the ensemble model. The potential distribution of O. hupensis snails after 2016 was predicted to be relatively concentrated in Yunnan Province by the RF model and relatively large by the MaxEnt model, and the distribution of O. hupensis snails predicted by the ensemble model was mostly the joint distribution of O. hupensis snails predicted by RF and MaxEnt models. Both RF and MaxEnt models are effective to predict the potential distribution of O. hupensis snails in Yunnan Province, which facilitates targeted O. hupensis snail control.

Customer churn prediction plays a vital role in modern business, accurately influencing strategic and operational decisions that influence customer loyalty to a service. Customer churn focuses on customer retention being more profitable than attracting new customers because long-term customers provide lower profits and costs while losing customers increases the costs and need to attract new customers. However, customer churn still occurs frequently and cannot be predicted. If customer churn is left unchecked, it will endanger the company or banking industry because it can cause loss of income, damage reputation, and decrease market share. Random Forest, a data mining technique, was used in this research because of its ability to predict and handle many variables. This research aims to predict customer churn using the Random Forest method with datasets from Europe, especially France, Spain, and Germany, hoping to benefit the banking industry by identifying customers at high risk of abandoning services. This research is expected to benefit business people from customer churn predictions. Especially in the banking industry, it can help identify customers at high risk of abandoning service. Thus, companies can take appropriate steps to retain these customers, increase customer retention, strengthen customer loyalty and optimize their business performance. The results of this research are an accurate system for predicting customer churn in the future. The research obtained accuracy results of 87% in predicting customer churn using accuracy testing in the form of a confusion matrix.

In all customer based industries, customer churn is considered as one of the most important and challenging concerns since it can lead to a serious profit loss. Therefore, developing accurate churn prediction models can significantly help Customer Relationship Management in planning effective retention campaigns and consequently helps in maximizing the profit of the service provider. In this paper, we propose the use of an Echo State Network (ESN) with a Support Vector Machine (SVM) training algorithm for predicting customer churn in telecommunication companies. The proposed approach is trained and tested based on two datasets: the first is a popular online available dataset while the second is obtained from a local service provider. Experiment results show that ESN with SVM readout outperform other popular machine learning models used in the literature for the same customer churn prediction problems.

Customer churn prediction is one of the most important elements of a company's Customer Relationship Management (CRM) strategy. In this study, two strategies are investigated to increase the lift performance of ensemble classification models, i.e. (i) using probability estimation trees (PETs) instead of standard decision trees as base classifiers, and (ii) implementing alternative fusion rules based on lift weights for the combination of ensemble member's outputs. Experiments are conducted for four popular ensemble strategies on five real-life churn data sets. In general, the results demonstrate how lift performance can be substantially improved by using alternative base classifiers and fusion rules. However, the effect varies for the different ensemble strategies. In particular, the results indicate an increase of lift performance of (i) Bagging by implementing C4.4 base classifiers, (ii) the Random Subspace Method (RSM) by using lift-weighted fusion rules, and (iii) AdaBoost by implementing both.

This research discusses the transformation of conventional banks to digital banking by emphasizing the importance of regulation and risk management. The method used is literature review, collecting and reviewing references related to OJK regulations governing digital banking services and risk management related to digital banks. The results show that strong regulations are needed to protect consumers and ensure the stability of the digital banking system. In addition, banks must implement adequate risk management to address threats such as cybersecurity, data protection, and operational risks. Good risk management allows banks to mitigate the negative impacts that may arise during the digitalization process. This research emphasizes the importance of regulation and comprehensive risk management in maintaining sustainability and customer trust in digital banking.