Dynamic modeling and forecasting of price elasticity based on time series analysis and machine learning

To create pricing policies, maximize resource allocation, and compete in a worldwide market, companies must have accurate estimates of price elasticity. Market supply and demand, seasonal fluctuations, economic cycles, policy control all challenge price elasticity models. Conventional statistical methods are unable to adequately represent dynamics in time series. In order to address the shortcomings of past approaches, this work presents the STL-GBM model, a dynamic price elasticity modeling and forecasting technique grounded on time series analysis and machine learning (ML). The model inputs trend and Seasonal and Trend decomposition using Loess (STL) decomposition into Gradient Boosting Machine (GBM) to anticipate price elasticity. High price elasticity prediction ability of STL-GBM is demonstrated by experimental validation on two real datasets, therefore highlighting the basic factors influencing price elasticity and providing companies with more informed decisions and market insight.