Elasticity Based Demand Forecasting and Price Optimization for Online Retail

We study a problem of an online retailer who observes the unit sales of a product, and dynamically changes the retail price, in order to maximize the expected revenue. Assuming the demand of the product is price sensitive, we are interested in the optimal pricing policy when future demand is uncertain. We build a system to investigate the relationship between retail price and demand and estimate the demand function. The system predicts demand and revenue at a given retail price. We formulate a revenue maximization problem over a discrete finite time horizon with discrete retail price. The optimal pricing policy is solved based on the predicted demand and revenue values. With computational experiments, we investigate the effect of optimal pricing policy to inventory management.