Price-demand elasticity as feature in machine learning model for demand forecasting

A system, comprising:

• a computer, comprising a processor and memory, the computer configured to:
• train, by a first iterative approach comprising cyclic boosting in multiplicative mode, a machine learning model to identify one or more external causal factors that influence demand for one or more products;
• train, by a second iterative approach comprising cyclic boosting in multiplicative mode that cycles through features and parameters, the machine learning model to generate one or more price-demand elasticity causal factors to predict a target outcome for a given product demand;
• predict, with the machine learning model, a demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more price-demand elasticity causal factors, wherein the machine learning model is a first machine learning model, the one or more price-demand elasticity causal factors is one or more first price-demand elasticity causal factors the target outcome is a first target outcome, the demand is a first demand and the computer is further configured to:
• deconfound historical demand data for the one or more products;
• train a second machine learning model to generate, based on the deconfounded historical demand data for the one or more products, one or more second price-demand elasticity causal factors to predict a second target outcome for the given product demand;
• predict, with the second machine learning model, a second demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more second price-demand elasticity causal factors;
• and
• shape the predicted second demand for the one or more products by altering one or more product price variables of the one or more products.

A non-transitory computer-readable storage medium embodied with software, the software when executed configured to:

• train, by a first iterative approach comprising cyclic boosting in multiplicative mode, a machine learning model to identify one or more external causal factors that influence demand for one or more products;
• train, by a second iterative approach comprising cyclic boosting in multiplicative mode that cycles through features and parameters, the machine learning model to generate one or more price-demand elasticity causal factors to predict a target outcome for a given product demand;
• predict, with the machine learning model, a demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more price-demand elasticity causal factors, wherein the machine learning model is a first machine learning model, the one or more price-demand elasticity causal factors is one or more first price-demand elasticity causal factors the target outcome is a first target outcome, the demand is a first demand and the software when executed is further configured to:
• deconfound historical demand data for the one or more products;
• train a second machine learning model to generate, based on the deconfounded historical demand data for the one or more products, one or more second price-demand elasticity causal factors to predict a second target outcome for the given product demand;
• predict, with the second machine learning model, a second demand for the one or more products based, at least in part, on the identified one or more external causal factors and the generated one or more second price-demand elasticity causal factors;
• and
• shape the predicted second demand for the one or more products by altering one or more product price variables of the one or more products.