Bank Marketing Classification

Implementing predictive models for banks to reduce operational costs while increasing campaign efficiency by targeting only customers with high potential to subscribe to a bank term deposit.

Data source: UCI Bank Marketing Dataset

Data preparation: Cleaning data, Data splitting, Encoding categorical columns, and Scaling numeric features.

EDA (Exploratory Data Analysis): Identify important features such as age distribution, call duration, previous campaign results, and job status.

Modeling: Develop 5 machine learning models, which will later be optimized with hyperparameter tuning and validated using recall and cross-validation.

Logistic Regression with hyperparameter Tuning
After comparing five types of models, Logistic Regression was selected as the best model based on the results of the performance evaluation. This selection was strengthened by the application of hyperparameter tuning to optimize its performance.

Recall score: 0.85
Reduces the chances of the marketing team missing potential targets.

Cross-validation accuracy: 0.82
The model performs stably on various subsets of data, not just on the training data.

Model ready to deploy
A notebook for new predictions has been prepared with an easy-to-use .pkl model.

Call Center Resource Efficiency
Call center agents no longer contact the entire customer list randomly.

Campaign Cost Reduction
The total number of calls required is drastically reduced resulting in a lower cost per conversion.

Increase Conversion Potential
Customers feel more relevant to the offer and are more likely to respond positively.