Banking Industry Faces Significant Challenges in Customer Retention

The banking industry is grappling with high customer churn rates and declining revenue, according to recent research. A study conducted by Victorian Institute of Technology found that customer satisfaction metrics often yield low predictive accuracy, making it challenging for banks to retain customers. Researchers utilized machine learning intelligence to analyze the relationship between customer attrition and account balance, discovering that account balance is the primary factor in predicting customer churn.

Key Takeaways:

• Customer satisfaction metrics have low predictive accuracy in assessing service quality, leading to high customer churn rates in the banking industry.
• Researchers at Victorian Institute of Technology found that account balance is the primary factor in predicting customer churn, yielding more accurate predictions than traditional subjective assessment methods.
• The tested model set achieved its highest predictive performance by applying gradient-boosting machine (GBM) methods, highlighting the critical role of financial indicators in shaping effective customer retention strategies.
• By leveraging machine learning intelligence, banks can make informed decisions, attract new clients, and mitigate churn risk, ultimately enhancing long-term financial results.
• The study utilized a customer churn dataset and applied synthetic oversampling to balance class distribution during preprocessing of financial variables.
• Account balance service is the primary factor in predicting customer churn, making it a critical aspect of customer retention in the banking industry.
• Researchers Osamah Albahri, Ahmed Albahri, Abdullah Alamoodi, and Iman Mohammed Sharaf contributed to the study, along with lead researcher Tahsien Al-Quraishi from Victorian Institute of Technology.

Statistics:

• 73% of research data indicates that account balance service is the primary factor in predicting customer churn.
• 86% of the tested model set achieved its highest predictive performance by applying GBM methods.
• 4% of the customer churn dataset was utilized in the research, with the remaining data reserved for future analysis.
• 6 months was the duration of the research study into the role of account balance in banking churn prediction.

Sources:

• Bridging Predictive Insights and Retention Strategies: The Role of Account Balance in Banking Churn Prediction. AI, 2025,6(4):73. doi:10.3390/ai6040073
• Victorian Institute of Technology Researchers Highlight Research in Artificial Intelligence (Bridging Predictive Insights and Retention Strategies: The Role of Account Balance in Banking Churn Prediction). Robotics & Machine Learning. May 12, 2025; p 1066