📚 Syllabus & Course Curriculum
Data Science & Analytics
Module-by-module breakdown of Reinforcement Learning for Dynamic Pricing, from foundations to a certified capstone project.
Economics
• Price elasticity, willingness to pay and the revenue-against-volume trade-off
• Dynamic, personalised and segmented pricing distinguished
• Two-sided markets where a price change moves both supply and demand
Demand
• Estimating demand curves from observational data and the endogeneity problem
• Building a pricing simulator and validating it against held-out periods
• Seasonality, competitor response and effects the simulator will miss
Bandits
• Multi-armed and contextual bandits as the natural first formulation
• Thompson sampling and UCB, and regret as the performance measure
• When the problem genuinely needs full RL instead of a bandit
Agents
• State design from inventory, time and demand signals
• Reward shaping for long-horizon revenue rather than immediate conversion
• Offline evaluation before any agent touches live traffic
Guardrails
• Price floors, ceilings and rate limits as hard constraints on the agent
• Algorithmic collusion risk and the competition law exposure it creates
• Fairness, price discrimination law and customer trust when pricing is visible
Earn government-registered certification in Reinforcement Learning for Dynamic Pricing
e-Certificate and e-Marksheet issued on successful completion.
