Abstract: In some aspects, the techniques described herein relate to a method including: receiving, from a plurality of data channels, client interaction data; preprocessing the client interaction data into a format consumable by one or more machine learning models; ingesting, by a sentiment scorer machine learning model, the client interaction data; generating, by the sentiment scorer machine learning model, a plurality of sentiment scores for a client associated with the client interaction data; ingesting, by a health scorer machine learning model, the plurality of sentiment scores; and outputting, by the health scorer machine learning model and based on the plurality of sentiment scores, a weighted health index score for the client associated with the client interaction data.

Abstract: Various methods, apparatuses/systems, and media for synthetic text generation are disclosed. A processor implements a text style transfer algorithm to first input data to generate complaints data from non-complaint emails data associated with a plurality non-complaint emails; converts the plurality of non-complaint emails into a first set of complaint emails based on implementing the text style transfer algorithm; implements a text generation model algorithm to second input data to generate a second set of complaint emails from a plurality of complaint emails; generates a set of synthetic complaint emails based on the generated first set of complaint emails and the second set of complaint emails; trains a model based on the generated synthetic complaint emails; and applies the trained model to a new set of emails to resolve class imbalance in automatic complaint identification from the new set of emails.