Adaptive adversarial system to structure competing interests

A non-transitory computer-readable storage medium comprising stored instructions thereon that, when executed by a processor system, cause the processor system to:

• collect user data describing how a user interacts with an online system;
• extract macro-level data from the user data, wherein macro-level data is associated with overall trends of a plurality of products, wherein the plurality of products are offered by the online system;
• generating, by machine learning model, supply-demand curves for the plurality of products from the macro-level data;
• identify, based on the supply-demand curves for the plurality of products, a placement for a product of the plurality of products in a GUI;
• generate a digital twin model of the user based on micro-level data of the user data, wherein the digital twin model is trained to mimic user interaction behavior with the online system based on the micro-level data;
• responsive to providing the product in the placement to the digital twin model, determine the user interaction behavior with the product based on mimic interaction behavior from the digital twin model;
• adjust the placement of the product in the GUI based on the mimic interaction behavior, wherein adjusting the placement includes updating a weight metric for the product according to the mimic interaction behavior;
• and
• provide for display the product in the placement in the GUI according to the weight metric.

A computing system, comprising

• a processor system comprised of one or more processors;
• and
• a non-transitory computer-readable storage medium comprising stored instructions thereon that, when executed by one or more processors, cause the processor system to:
• collect user data describing how a user interacts with an online system;
• extract macro-level data from the user data, wherein macro-level data is associated with overall trends of a plurality of products, wherein the plurality of products are offered by the online system;
• generate, by a machine learning model, supply-demand curves for the plurality of products from the macro-level data;
• identify, based on the supply-demand curves for the plurality of products, a placement for a product of the plurality of products in a GUI;
• generate a digital twin model of the user based on micro-level data of the user data, wherein the digital twin model is trained to mimic user interaction behavior with the online system based on the micro-level data;
• responsive to providing the product in the placement to the digital twin model, determine the user interaction behavior with the product based on mimic interaction behavior from the digital twin model;
• adjust the placement of the product in the GUI based on the mimic interaction behavior, wherein adjusting the placement includes updating a weight metric for the product according to the mimic interaction behavior;
• and
• provide for display the product in the placement in the GUI according to the weight metric.