Vitamins product pricing optimization

A supplement manufacturer was launching a new sleep medication product but lacked a data-driven approach to set optimal pricing. Their traditional methods relied on competitor analysis and limited market research, potentially leading to missed opportunities or profit erosion.

The challenge was compounded by the need to consider their entire product portfolio - pricing the new product incorrectly could cannibalize sales from existing products. They needed a systematic approach that would account for cross-product effects and market dynamics.

Without proper pricing optimization, they risked either leaving money on the table with underpricing or losing market share with overpricing, especially in a highly competitive supplements market.

I developed a comprehensive pricing optimization framework using Bayesian analysis and mixed-integer programming (MIP). The solution started with gathering historical sales data of existing sleep medications and competitor pricing strategies to understand market dynamics.

The Bayesian framework allowed me to estimate demand-price relationships with uncertainty quantification, which was crucial given the limited data available for a new product launch. I incorporated informative priors based on similar existing products to improve the demand curve estimates.

The core of the solution was a MIP model that optimized pricing across the entire medication portfolio. This considered demand-price relationships, cost constraints, and the potential for cannibalization between products. The model explored multiple objective functions including maximizing total revenue and maximizing gross margin, allowing the client to understand trade-offs between sales volume and profitability.