Readings

Pre-Workshop and Supplementary Materials

Pre-Workshop Readings

Please review these materials before the workshop begins.

Required

1. Introduction to Machine Learning
   • A visual introduction to machine learning
   • Estimated time: 15 minutes
2. Reproducible Research
   • Wilson et al. (2017). “Good enough practices in scientific computing.” PLOS Computational Biology.
   • Link to paper
   • Focus on: Sections 1-3

Recommended

3. Python for Data Science
   • Python Data Science Handbook (free online)
   • Focus on: Chapter 3 (Pandas) and Chapter 5 (Machine Learning)
4. Agent-Based Modeling
   • Macal, C.M. and North, M.J. (2010). “Tutorial on agent-based modelling and simulation.” Journal of Simulation.
   • Link to paper

Day-by-Day References

Day 1: Foundations

• Quarto documentation
• Google Colab introduction

Day 2: Machine Learning

• scikit-learn documentation
• Cross-validation tutorial

Case Study Paper:

• Roe, Y., Lee, S., Kim, C., & Lee, J. (2025). “Drug shortage in South Korea: machine learning-based prediction models and analysis of duration and causal factors.” Frontiers in Pharmacology, 16, 1608843.
  • Link to paper
  • Demonstrates Random Forest with Bayesian optimization for predicting drug shortage duration (62% accuracy) and causes (>70% F1). Top predictors: shortage frequency, import status, alternative drug availability. We replicate this approach in Notebook 05.

Day 3: Integration

• Mesa: Agent-based modeling in Python
• Additional resources provided by Dr. Ozawa

Day 4: ABM Deep Dive

• Materials provided by Dr. Ozawa

Supplementary Resources

Python Basics

• Python for Everybody (free course)
• Real Python tutorials

Data Science

• Kaggle Learn
• Google’s Machine Learning Crash Course

Supply Chain Modeling

• Shared via Google Drive