Learners will evaluate the performance trade-offs between accuracy, latency, and interpretability of at least three AI techniques on the same dataset and recommend the optimal choice.

Learners will apply linear programming optimization for product mix decisions and evaluate competing prescriptive scenarios using weighted-scoring models for stakeholder presentation.

Learners will apply genetic algorithms to inventory-replenishment problems and compare results with linear programming baseline.

Learners will train Q-learning agents in grid-world supply-chain simulations and report cumulative reward improvements over epochs.

Learners will evaluate convergence speed vs. solution quality trade-offs and optimize ε-greedy parameters for reinforcement learning performance.

Learners will analyze observational data with propensity-score matching to estimate treatment effects and present a causal impact report.

Learners will evaluate the validity of causal assumptions (ignorability, overlap, positivity) for a given business experiment and suggest mitigation steps.

Learners will apply the PC or FCI algorithm to a marketing dataset, interpret the learned causal graph, and validate edges with domain experts.

Learners will evaluate robustness of discovered relationships via bootstrap resampling and report stability metrics.

Learners will design and conceptually design and plan online A/B tests with proper tracking and statistical methodology.

Learners will evaluate practical vs. statistical significance and make rollout decisions. That optimize both business value and resource allocation.

Learners will understand the theoretical foundations of simulation modeling and prepare to build Monte Carlo models for business applications.

Learners will build functional Monte Carlo simulation models using Excel and Python, executing 10,000+ iterations to generate probability distributions for project ROI analysis.

Learners will master sensitivity analysis through tornado charts and convergence testing to determine optimal iteration counts for reliable simulation results.

Learners will integrate all Monte Carlo simulation skills through comprehensive practical applications and demonstrate mastery via course-level graded assessment covering all learning outcomes.

You will build a Marketing Mix Optimization Framework that integrates causal inference, prescriptive optimization, and Monte Carlo simulation into a single decision support deliverable. Working with real marketing channel spend and conversion data, you will validate causal effects, recommend an optimal budget allocation, and quantify the risk of the proposed plan. The final deliverable combines a Python analysis notebook with an executive summary suitable for C-level presentation.