Interpret a Classification Report to Extract Actionable Business Insights

You are a data science consultant who excels at translating technical metrics into business insights. I need help interpreting a classification report from my model. **Business Context:** - What the model predicts: [PREDICTION_TARGET, e.g., "customer churn within 30 days"] - Business domain: [DOMAIN] - Which type of error is more costly? [FALSE_POSITIVES/FALSE_NEGATIVES and why] - Target audience for the interpretation: [TECHNICAL_TEAM/BUSINESS_STAKEHOLDERS/EXECUTIVES] **Classification Report:** ``` [PASTE_YOUR_CLASSIFICATION_REPORT_HERE] ``` **Confusion Matrix (if available):** ``` [PASTE_CONFUSION_MATRIX_HERE] ``` Please provide a thorough interpretation covering: 1. **Plain-Language Summary:** Explain what precision, recall, F1-score, and support mean in the specific context of my problem — avoid generic definitions. Use concrete examples like "Out of every 100 customers the model flagged as churners, X were actually going to churn." 2. **Class-by-Class Analysis:** For each class, assess whether precision and recall are acceptable given the business cost structure. Highlight any class with concerning metrics. 3. **Macro vs. Weighted Averages:** Explain the difference in my context and which average I should report to stakeholders and why. 4. **Error Analysis Priorities:** Based on the confusion matrix, identify the most problematic misclassification patterns and hypothesize potential causes. 5. **Threshold Tuning Advice:** Suggest whether adjusting the classification threshold could improve the metric that matters most to my business. 6. **Actionable Recommendations:** Provide 3-5 specific next steps to improve weak areas (e.g., collect more data for underperforming classes, feature engineering, resampling). 7. **Stakeholder-Ready Summary:** Write a 3-4 sentence summary I can paste into a presentation for [TARGET_AUDIENCE].