Method and system for generation of at least one output analytics for a promotion

A system for generation of at least one output analytic for promotional materials, the system comprising one or more processors and a data storage device, the one or more processors configured to:

• receive historical data related to one or more products and a plurality of previous promotional materials;
• receive, from a user one or more input parameters related to the promotional materials;
• train and instantiate a plurality of machine learning a plurality of promotion forecasting models comprising at least a Random Forest model and a ridge regression model, with a selection training set, the selection training set comprising the historical data and the one or more input parameters, wherein the ridge regression includes a prior on coefficients of the input parameters,
• select, using the machine learning model, a configuration and a layout for the one or more products on the promotional materials, the selection comprising:
• assigning a prominence weight to each of the one or more products;
• normalizing the prominence weight for each of the one or more products;
• determining a block structure comprising a plurality of block locations for the promotional materials based on the prominence weight of each of the one or more products;
• determining a product block location from the plurality of block locations for each of the products on the promotional materials based on the prominence weight of each of the one or more products, wherein determining the product block location is further based on, at least in part, a plurality of weights assigned to each of the product blocks;
• and
• outputting the promotional materials including the block structure based on the selection of the configuration and layout selected using the machine learning model;
• wherein the one or more processors are further configured to, iteratively, by the processor:
• receive adjustment information to the outputted promotional materials from a user via a user interface, wherein the adjustment information comprises at least one of the following:
• removing a product from being displayed in the promotional materials, changing the length of the promotional materials, changing the prominence weighting of any of the product blocks, and changing the properties of the product blocks including the area, the location and the conspicuity of the product blocks;
• store the received adjustment information in a database, and updating the stored adjustment information in the database;
• supply the stored adjustment information to the machine learning model;
• re-run the machine learning model using the supplied adjustment information;
• regenerate the promotional materials using the machine learning model;
• and
• output the promotional materials including the block structure based on the selection of the configuration and the layout selected using the machine learning model.

A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to execute the steps of:

• receiving historical data related to one or more products and a plurality of previous promotional materials;
• receiving, from another computer device communicatively coupled to the computer via a network, one or more input parameters related to the promotional materials from a user;
• training and instantiating a machine learning model comprising a plurality of promotion forecasting models comprising at least a Random Forest model and a ridge regression model, wherein the ridge regression includes a prior on coefficients of the input parameters with a selection training set, the selection training set comprising the historical data and the one or more input parameters,
• selecting, using the machine learning model, a configuration and a layout for the one or more products on the promotional materials, the selection comprising:
• assigning a prominence weight to each of the one or more products;
• normalizing the prominence weight for each of the one or more products;
• determining a block structure comprising a plurality of block locations for the promotional materials based on the prominence weight of each of the one or more products;
• determining a product block location from the plurality of block locations for each of the products on the promotional materials based on the prominence weight of each of the one or more products, wherein determining the product block location is further based on, at least in part, a plurality of weights assigned to each of the product blocks;
• and
• outputting the promotional materials including the block structure based on the selection of the configuration and layout selected using the machine learning model
• wherein instructions, when executed by a computer, cause the computer to execute the further steps of, iteratively, by the processor:
• receiving adjustment information to the outputted promotional materials from a user via a user interface, wherein the adjustment information comprises at least one of the following:
• removing a product from being displayed in the promotional materials, changing the length of the promotional materials, changing the prominence weighting of any of the product blocks, and changing the properties of the product blocks including the area, the location and the conspicuity of the product blocks;
• storing the received adjustment information in a database, and updating the stored adjustment information in the database;
• supplying the stored adjustment information to the machine learning model;
• re-running the machine learning model using the supplied adjustment information;
• regenerating the promotional materials using the machine learning model;
• and
• outputting the promotional materials including the block structure based on the selection of the configuration and the layout selected using the machine learning model.