{"id":3463,"date":"2023-08-31T11:13:00","date_gmt":"2023-08-31T11:13:00","guid":{"rendered":"https:\/\/neuraldesigner.com\/learning\/bank-churn-modeling\/"},"modified":"2026-02-12T12:50:27","modified_gmt":"2026-02-12T11:50:27","slug":"bank-churn","status":"publish","type":"learning","link":"https:\/\/www.neuraldesigner.com\/learning\/examples\/bank-churn\/","title":{"rendered":"Reduce customer churn in a bank using machine learning"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

This example uses customer data from a bank to build a predictive model for identifying clients who are likely to churn. More specifically, the objective is to anticipate customer behavior before they decide to leave. By doing so, the bank can act proactively rather than reactively.<\/p>

As we know, acquiring a new client is significantly more expensive than retaining an existing one. In fact, customer acquisition costs often exceed retention costs by a wide margin. Therefore, it is highly advantageous for banks to understand the factors that lead customers to leave the company. Moreover, early detection of dissatisfaction allows timely intervention.<\/p>

In this context, Churn prevention<\/a> enables financial institutions to design targeted loyalty programs and personalized retention campaigns. At the same time, it helps allocate marketing resources more efficiently. Consequently, banks can increase customer satisfaction, reduce attrition rates, and ultimately maintain long-term profitability.<\/p>

Contents<\/h3>
  1. Application type<\/a>.<\/li>
  2. Data set<\/a>.<\/li>
  3. Neural network<\/a>.<\/li>
  4. Training strategy<\/a>.<\/li>
  5. Model selection<\/a>.<\/li>
  6. Testing analysis<\/a>.<\/li>
  7. Model deployment<\/a>.<\/li><\/ol>

    This example is solved with Neural Designer<\/a>. To follow it step by step, you can use the free trial<\/a>.<\/p><\/section>

    1. Application type<\/h2>

    The variable to be predicted is binary (churn or loyal).\u00a0<\/span>Therefore this is a <\/span>classification<\/a> project.<\/span><\/p>

    The goal here is to model churn probability, conditioned on the customer features.<\/p><\/section>

    2. Data set<\/h2>

    The data set contains information for creating our model. We need to configure three things here:<\/p>