3. Optimal policy targeting with predictive machine learning

• 3.1. Predicting land acquisition cost and forest change across Massachusetts
  • 3.1.1. Understand how data on costs and threat can help with policy targeting
  • 3.1.2. Meet the modeling packages
  • 3.1.3. Examine the parcel data
  • 3.1.4. Fit explanatory models with statsmodels
  • 3.1.5. Fit predictive models with scikit-learn
  • 3.1.6. Improve your predictions (optional)
  • 3.1.7. Predict forest change
  • 3.1.8. Wrap up
• 3.2. Optimality of policy targeting: simulating incentives to avoid carbon loss
  • 3.2.1. Understand how targeting can affect policy outcomes
  • 3.2.2. Frame the problem and analysis
  • 3.2.3. Estimate parcel-level cost-benefit ratio
  • 3.2.4. Draw the supply curve for avoided emissions
  • 3.2.5. Model the implications of policy design choices
  • 3.2.6. Write up your findings
  • 3.2.7. Improve the scenarios (optional)
  • 3.2.8. Wrap up