Categorical Data Transformation and Clustering for Machine Learning using Natural Language Processing

In a digital medium environment to improve operation of a computing device to enable the computing device to perform machine learning using categorical data, the computing device comprising:

• a processing system;
• and
• a computer-readable storage medium having instructions stored thereon that, responsive to execution by the processing system, configures the processing system to execute instructions to implement modules including:
• a natural language processing module to convert categorical data having at least one non-numerical data type for a number of classes of a categorical variable into numerical data using natural language processing;
• a clustering module to generate data having a plurality of latent classes by clustering the numerical data into a number of clusters that is smaller than the number of classes;
• and
• a machine learning module to process the generated data having the plurality of latent classes by a model using machine learning.

In a digital medium environment to improve machine learning operation to employ categorical data, a system comprising:

• means for converting categorical data that includes a categorical variable having a non-numerical data type for a number of classes into numerical data using natural language processing;
• means for generating data having a plurality of latent classes by clustering the numerical data into a number of clusters that is smaller than the number of classes;
• and
• means for training a model using machine learning by processing the generated data having the plurality of latent classes.