Price Elasticity of Demand and Dynamic Pricing in Online Retail: A Machine Learning Approach to Revenue Optimization

Pricing is among the most powerful levers a retailer controls, yet many online retailers still set prices with fixed markups. This paper measures how sensitive demand is to price and tests whether that sensitivity can guide better prices. Using weekly product-level transactions of a UK-based online retailer, price elasticity is estimated three ways: a log-log fixed-effects regression, a gradient-boosting demand model with counterfactual price perturbation, and double machine learning that adjusts for seasonality and product effects. Elasticity is then compared across price tiers and seasons, and a guard-railed dynamic pricing policy, limited to ±20% changes inside each product's historical price range, is simulated on a chronological hold-out period. Results: the pooled elasticity is −3.24 (95% CI −3.74 to −2.73), so demand is strongly priceelastic, although volume discounts to wholesale customers probably exaggerate its size; double machine learning agrees (−3.19) but the machine learning counterfactual does not (positive sign); gradient boosting lowers forecast error (WAPE) by 16.8% against a historical-mean baseline; and the simulated pricing policy shows revenue gains of 77%, which are implausibly large and are read as artefacts of the estimated elasticity and the model, not as achievable gains. Implications, limits of observational price data and the need for controlled price experiments are discussed.