Customer Segmentation and Prediction with Logistic Regression and Flask Technology

The project centers on predicting customer churn using a dataset of 7,044 entries and 21 columns, integrated into a user-friendly Flask application. The system allows users to input data manually or via CSV file uploads, facilitating easy interaction and analysis. Employing machine learning algorithms such as logistic regression and correlation analysis, the model achieves high accuracy in forecasting churn, with a precision of 95.57% and an overall accuracy of 92.08%. The application’s intuitive interface and predictive capabilities enable businesses to anticipate customer attrition, optimize retention strategies, and enhance decision-making processes. By offering real-time feedback and streamlined outputs, this research significantly contributes to customer relationship management, empowering organizations across various industries to mitigate churn risks and drive sustainable growth. This system not only improves operational efficiency but also provides actionable insights that are critical for maintaining competitive advantage. Continuous monitoring and model refinement ensure that the tool remains effective in adapting to changing business environments, further enhancing its value for long-term success.