Aspects of the present disclosure relate to a demand forecasting system. The demand forecasting system may include components for developing forecasting models, generating demand forecasts, and handling outputs of demand forecasting models. In some embodiments, the demand forecasting system may include a model training system and one or more components that can be used by the model training system to improve model performance.

A demand prediction display device includes: a memory configured to store instructions; and one or more processors configured to execute the instructions to: predict a demand of a consumer of a product in a prediction target period by using purchase record data of the product by the consumer; predict a demand for a wholesale shipment of the product in the prediction target period by using wholesale shipment record data of the product by a wholesaler; predict a demand for a manufacturer shipment in the prediction target period by using manufacturer shipment record data of the product by a manufacturer; and display a prediction result of the demand of the consumer, a prediction result of the demand for the wholesale shipment, and a prediction result of the demand for the manufacturer shipment on a display device on a common time axis.

The system may create marketing campaigns based on inventory data and/or sales data for a product. The system may compare the inventory data for the product or the sales data for the product to inventory threshold data or sales threshold data, respectively. The system may adjust a marketing campaign for the product based on a relationship between at least one of the inventory data and the inventory threshold data, or the sales data and the sales threshold data. The marketing campaigns may be further based on weather data, traffic data, event data, seasonal data, holiday data, calendar data, trend data and/or any other data.

An information processing apparatus includes an acquisition unit that acquires feature values related to a target product and similar product information related to a product similar to the target product, a first prediction unit that calculates, by using a plurality of prediction models, a prediction value for each prediction model from the feature values, a selection unit that selects a metamodel related to the similar product information, and a second prediction unit that performs, by using the selected metamodel, prediction related to the target product from the prediction values calculated by the prediction models.