Engineer AI Models: Explain, Tune & Experiment

Engineer AI Models: Explain, Tune & Experiment prepares program and project managers to guide AI projects beyond “just working” toward being trusted, explainable, and reproducible. You’ll learn how feature engineering and hyperparameter tuning improve model performance, how explainability methods like SHAP and LIME build stakeholder confidence, and how structured experimentation ensures reliable results. Through real-world scenarios — from boosting fraud detection F1 scores, to presenting credit approval models to risk committees, to planning experiments in Jupyter — you’ll gain the skills to ask the right questions, guide technical teams, and translate complex model outputs into business impact. By the end, you’ll know how to move AI projects from black box to business-ready

• Understand feature engineering to improve AI model performance
• Apply hyperparameter tuning to optimize models
• Use explainability techniques to build stakeholder confidence
• Design structured experiments for reliable and reproducible results

• Basic familiarity with AI and ML terminology
• Readiness for applied exercises and case-based work