Summary: The project focused on evaluating the effectiveness of a Portuguese bank's direct marketing campaigns through data-driven insights. By employing data science methodologies, the project aimed to uncover patterns in customer behavior, optimize campaign targeting, and enhance subscription rates for bank term deposits.
Goals of the Project:
Pattern Identification: Analyzing customer attributes like marital status, gender, and job type to understand their impact on campaign success.
Model Evaluation: Applying logistic regression and random forest models to predict subscription outcomes and measure their accuracy.
Optimization: Utilizing insights to refine targeting strategies for increased subscription rates and more efficient resource allocation.
Tools Used: Descriptive Analytics: Exploring data distributions and patterns, including histograms for age distribution.
Prescriptive Analytics: Employing logistic regression and random forest classifiers to forecast campaign outcomes.
Visualization: Creating graphical representations to illustrate call patterns by day, customer job categories, and previous campaign outcomes.
Conclusion: The project delved into the intricacies of a Portuguese bank's direct marketing campaigns, with a focus on data analysis and predictive modeling. Through rigorous exploration of customer attributes and campaign history, valuable insights were gained. Both logistic regression and random forest models demonstrated strong accuracy, highlighting the potential for optimizing targeting efforts. The project's findings suggest a need for refined strategies to enhance subscription rates and resource allocation, ultimately driving better campaign performance and effectiveness.