- 🔍 Understand the Business Context: Identify factors impacting customer retention and churn in the utility industry.
- 🔮 Formulate Hypotheses: Explore the impact of price changes on customer churn.
- 📊 Data Science Problem Formulation: Define the problem as a predictive modeling task to identify customers at risk of churning due to price sensitivity.
- 📧 Email to AD: Summarize thoughts on testing the hypothesis, focusing on data requirements and analytical approaches.
- 🔍 Data Exploration: Understand the data types, distributions, and statistical characteristics.
- 💰 Price Sensitivity and Churn Correlation: Investigate price sensitivity measures and correlate them with churn.
- 📊 Key Findings Summary: Condense key findings into a half-page summary. Suggest additional data sources for better insights.
- 🔧 Feature Engineering: Enhance features related to price sensitivity and churn.
- 🤖 Model Training: Utilize Random Forest Classifier to predict churn probability.
- 📈 Performance Evaluation: Assess model performance, justify choice of metrics, and consider the financial impact of the model's predictions.
- 💡 Model Advantages and Disadvantages: Highlight pros and cons of using a Random Forest for this use case.
- 📓 Abstract Slide Creation: Summarize project findings for stakeholders.
- 🎯 Focus on Actionable Insights: Emphasize crucial metrics, actionable recommendations, and potential impact on the client's business (e.g., potential cost savings through targeted discounts).