Systems and methods for optimizing wearable item selection in electronic clothing transactions platform

A computer-implemented method for assigning wearable items in an electronic clothing transactions platform, the method comprising:

• determining, by one or more processors, information regarding historically shipped wearable items;
• utilizing, by the one or more processors, a neural network trained based on information regarding the historically shipped wearable items to determine an average percentage indicating how many wearable items have been used per number of wearable items shipped;
• utilizing, by the one or more processors, the trained neural network to determine an average predictive wearability metric for wearable items indicative of a propensity of a user to use the wearable items;
• obtaining, by the one or more processors, information regarding a first pairing including a first unique user identifier and a first wearable item, wherein the information comprises:
• (i) a first predictive wearability metric associated with the first unique user identifier and the first wearable item, and (ii) a first percentage indicating how many wearable items have been used by the first user per number of wearable items shipped to the first user;
• converting, by the one or more processors, the first predictive wearability metric to a first squashed wearability metric by comparing the first predictive wearability metric to the average predictive wearability metric, and comparing the first percentage indicating how many wearable items have been used by the first user per number of wearable items shipped to the first user to the average percentage indicating how many wearable items have been used per number of wearable items shipped;
• and
• determining, by the one or more processors, whether to assign the first wearable item to the first unique user identifier based on the first squashed wearability metric and/or the first predictive wearability metric.

A computer system for assigning wearable items in an electronic clothing transactions platform, the computer system comprising:

• a data storage device storing processor-readable instructions;
• and
• a processor configured to execute the instructions to perform a method including:
• determining information regarding historically shipped wearable items;
• utilizing a neural network trained based on information regarding the historically shipped wearable items to determine an average percentage indicating how many wearable items have been used per number of wearable items shipped;
• utilizing the trained neural network to determine an average predictive wearability metric for wearable items indicative of a propensity of a user to use the wearable items;
• obtaining information regarding a first pairing including a first unique user identifier and a first wearable item, wherein the information comprises:
• (i) a first predictive wearability metric associated with the first unique user identifier and the first wearable item, and (ii) a first percentage indicating how many wearable items have been used by the first user per number of wearable items shipped to the first user;
• converting the first predictive wearability metric to a first squashed wearability metric by comparing the first predictive wearability metric to the average predictive wearability metric, and comparing the first percentage indicating how many wearable items have been used by the first user per number of wearable items shipped to the first user to the average percentage indicating how many wearable items have been used per number of wearable items shipped;
• and
• determining whether to assign the first wearable item to the first unique user identifier based on the first squashed wearability metric and/or the first predictive wearability metric.

A non-transitory computer-readable medium containing instructions that, when executed by a processor, cause the processor to perform a method comprising:

• determining information regarding historically shipped wearable items;
• utilizing a neural network trained based on information regarding the historically shipped wearable items to determine an average percentage indicating how many wearable items have been used per number of wearable items shipped;
• utilizing the trained neural network to determine an average predictive wearability metric for wearable items indicative of a propensity of a user to use the wearable items;
• obtaining information regarding a first pairing including a first unique user identifier and a first wearable item, wherein the information comprises:
• (i) a first predictive wearability metric associated with the first unique user identifier and the first wearable item, and (ii) a first percentage indicating how many wearable items have been used by the first user per number of wearable items shipped to the first user;
• converting the first predictive wearability metric to a first squashed wearability metric by comparing the first predictive wearability metric to the average predictive wearability metric, and comparing the first percentage indicating how many wearable items have been used by the first user per number of wearable items shipped to the first user to the average percentage indicating how many wearable items have been used per number of wearable items shipped;
• and
• determining whether to assign the first wearable item to the first unique user identifier based on the first squashed wearability metric and/or the first predictive wearability metric.