Systems and methods for experiment aspect prediction

Abstract

Disclosed herein are computer systems and computer-implemented methods for training a machine learning model to predict an aspect of an experiment. The method may comprise training a machine learning model to predict an aspect of an experiment. The method may comprise (i) grouping data retrieved from a plurality of sources into one or more groups based on a plurality of data types, (ii) identifying a plurality of entities of the data, (iii) generating modality data for a group of the one or more groups, (iv) generating a plurality of tokens from the modality data, (v) ordering the plurality of tokens based on the plurality of entities to form a token sequence based on one or more shared entities associated with the plurality of tokens, and (vi) training the machine learning model on the token sequence to predict the aspect of the experiment.

Images