Interactive Textbook Module Syllabus

Data-Driven Targeting

Move from 'who are our segments?' to 'which customers should we act on?' Build classification models that predict individual-level outcomes, evaluate them with confusion matrices and cost-sensitive metrics, and set decision thresholds that maximize business value — not just accuracy.

⏱️ ~55 min reading & interactives 📑 11 sections 🎓 Level: Advanced undergraduate 📐 Math: Formulas shown 📚 Courses: Marketing Analytics, Predictive Analytics & ML 🏷️ Topics: Machine learning & prediction, Segmentation & clustering

Chapter Section Outline (11 Sections)

Topics and managerial frameworks covered in Data-Driven Targeting:

1. From Segments to Decisions
2. The Targeting Problem = Classification
3. Logistic Regression: The Workhorse Classifier
4. Decision Trees: When Rules Beat Equations
5. Measuring What Matters: Confusion Matrices
6. Beyond Accuracy: Precision, Recall, and the F1 Trade-Off
7. Threshold Tuning: Where Statistics Meets Strategy
8. Cost-Sensitive Targeting: Making Errors Pay
9. Targeting in the Age of AI
10. Case Application — SpringLeaf Insurance Policy Upgrade Targeting
11. Targeting in Practice

Interactive Concept Mini-Widgets Embedded in This Chapter (2)

Students manipulate these interactive visual simulations directly inside the chapter reading before answering gated check-in questions:

Confusion Matrix Explorer

Students drag a threshold slider and watch a confusion matrix, precision, recall, accuracy, and F1 score update in real-time. Uses 500 pre-generated churn probability scores with known labels.

Teaches: accuracy alone is misleading; threshold choice drives the precision- recall trade-off; the default 0.50 is arbitrary.

Cost-Asymmetry Simulator

Three sliders (FP cost, FN cost, TP revenue) drive a real-time profit curve showing expected profit at each threshold. A vertical line marks the optimal threshold (T*) and contrasts it with the naïve 0.

Teaches: cost asymmetry drives threshold asymmetry; revenue dramatically shifts the optimal operating point; the 0.50 default is almost never right.

Paired Browser-Based Analytics Calculators (3)

This chapter connects directly to these full MktPraxis analytical apps (with pre-loaded business case scenarios, CSV upload, and reproducible Python export):

🎯 Logistic Regression

Predict binary outcomes like Churn vs. Retain.

Pre-loaded Business Scenarios: Influencer Posts: What Makes a Story Drive a Sale? · B2B Email Sequences: Predicting Demo Bookings · Digital Promo A/B Test: High Incentive vs Standard Offer · Subscription Churn: Predicting Customer Attrition · Event Marketing: Predicting Registration Conversion · RFM-Based Purchase Prediction: Who Buys Next? · SignalPath MarTech: Which Leads Actually Close? · Will They Come Back? Predicting Season-Membership Renewal

🌳 Decision Tree Classifier

Build and interpret classification trees to segment customers and predict outcomes.

Pre-loaded Business Scenarios: Customer Churn Prediction - FitLife Gym · B2B Lead Scoring - CloudSync SaaS · Customer Segment Classification - Artisan Coffee Co

🎯 Classification Threshold Lab

Interactively explore how the classification threshold affects profit vs. cost trade-offs in binary ML models. Find the optimal T* that maximises net profit.

Pre-loaded Business Scenarios: FreshBox — DTC Snack Subscription · StreamFlow — Streaming Service · Kiteline Analytics — Enterprise-Tier B2B Analytics SaaS