Systems and Methods Providing a ConjointNet Architecture for Enhanced Conjoint Analysis for Preference Prediction with Representation Learning

A system for generating predicted preferences, the system comprising:

• one or more processors;
• and
• a non-transitory, computer-readable medium storing instructions that, when executed by the one or more processors, cause the one or more processors to:
• implement a conjoint architecture comprising:
• an autoencoder trained to transform input data including one or more choices and one or more features into a latent representation, and
• a choice classification network trained to predict one or more predicted preferences from the latent representation extracted by the autoencoder;
• and
• output, from the choice classification network, the one or more predicted preferences.

A computing program product for generating predicted preferences, the computing program product comprising machine-readable instructions stored on a non-transitory computer readable memory, which when executed by a computing device, causes the computing device to carry out steps comprising:

• implementing a conjoint architecture comprising:
• an autoencoder trained to transform input data including one or more choices and one or more features into a latent representation, and
• a choice classification network trained to predict one or more predicted preferences from the latent representation extracted by the autoencoder;
• and
• outputting, from the choice classification network, the one or more predicted preferences.