Systems and methods for algorithmic pricing

A system comprising:

• one or more processors;
• and
• one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processor, cause the one or more processers to perform functions comprising:
• calculating a halo weight for at least one item of a set of items by dividing a halo revenue by a unit metric, wherein the halo revenue is generated by the at least one item, wherein the unit metric comprises a number of units sold of the at least one item, and wherein the halo weight comprises an effect that sales of the at least one item has on sales of the set of items;
• calculating an item-wise elasticity for the at least one item of the set of items;
• calculating a line-wise elasticity for the at least one item of the set of items;
• calculating an aggregate elasticity for the at least one item using the item-wise elasticity and the line-wise elasticity;
• accessing a database comprising sales data and price data for the set of items;
• dividing the sales data and the price data for the at least one item into a training data set and a test data set;
• training different models on the training data set;
• determining respective accuracy of each model of the different models, as trained, using the test data set;
• calculating a demand forecast for the at least one item of the set of items using a most accurate model of the different models, as trained;
• optimizing an objective function comprising the halo weight, the aggregate elasticity, the demand forecast, at least one external constraint, a linearized elasticity of the at least one item, and an optimized price of the at least one item;
• adjusting at least one price of the at least one item based on the objective function, as optimized;
• and
• displaying the at least one price, as adjusted, for the at least one item on a display device of a user.