Size and fitting recommendation systems and method for fashion products

A size and fitting recommendation system for fashion products, the system comprising:

• a memory having computer-readable instructions stored therein;
• and
• a processor configured to:
• access purchase and content data of a plurality of first fashion products purchased by at least one user;
• identify a first set of fashion products associated with a first purchase record and a second set of fashion products associated with a second purchase record, wherein the first purchase record is greater than the second purchase record, wherein at least one second fashion product of the second set of fashion products (i) has a second type with greater similarity to a first type of at least one first fashion product of the first set of fashion products than with a third type of a third set of fashion products (ii) is purchased less frequently than any of the first fashion products by a set of users, the at least one first fashion product being purchased more frequently than the at least one second fashion product, wherein the first and second sets of fashion products are previously purchased, and the greater similarity being based on a criterion being satisfied;
• generate an observable user vector and a latent user vector for the first and second sets of fashion products, wherein each of the observable user vector(s) is generated based upon respective observable features data, and wherein each of the latent user vector(s) is generated based upon respective latent features data;
• train an autoencoder model configured to (i) learn an initial compression, by densely representing the observable user vector and the latent user vector, (ii) learn a subsequent decompression, and (iii) generate at least one size and fitting recommendation for the at least one fashion product of the second set of fashion products, wherein the compression causes a reduction, during the training, of a number of dimensions of each of the observable user vector and the latent user vector;
• and
• display, to the at least one user at a user interface, the at least one generated recommendation, comprising personalized size information across brands, fit type, brand type, product type, or combinations thereof of the at least one second fashion product of the second set of fashion products.

A computer-implemented method for recommending size and fitting information for fashion products, the method comprising:

• identifying a first plurality of fashion products and a second plurality of fashion products, the second plurality of fashion products (i) having a second type with greater similarity to a first type of the first plurality of fashion products than with a third type of a third set of fashion products (ii) purchased less frequently than any of the first fashion products by a set of users, wherein the first and second plurality of fashion products are previously purchased, and the greater similarity being based on a criterion being satisfied;
• generating an observable user vector and a latent user vector for the first and second plurality of fashion products, wherein the observable user vector is generated based upon respective observable features data, and wherein the latent user vector is generated based upon respective latent features data;
• training an autoencoder model configured to learn an initial compression, by densely representing the observable user vector and the latent user vector, and learn a subsequent decompression, wherein the compression causes a reduction, during the training, of a number of dimensions of each of the observable user vector and the latent user vector;
• generating at least one size and fitting recommendation of the second plurality of fashion products based upon (i) the observable user vector, (ii) the trained model, and (iii) the latent user vector;
• and
• displaying, to the at least one user at a user interface, the at least one generated recommendation, comprising personalized size information across brands, fit type, brand type, product type, or combinations thereof of one or more of the second plurality of fashion products.