Forecasting and mitigating concept drift using natural language processing

A computer system, the computer system comprising:

• one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more computer-readable tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:
• automatically detecting features and variables considered by a target machine learning model, wherein concept drift detection includes one or more of Local Interpretable Model-Agnostic Explanations (LIME), and Shapley Additive ex-Planations (SHAP);
• automatically storing and updating a configurable corpus of relevant documents pertaining to a domain of the target machine learning model, wherein the storing and updating includes processing by annotating, splitting, and modifying of format, based on the domain of the target machine learning model;
• automatically extracting event types and corresponding time stamps from the configurable corpus of relevant documents, by natural language processing techniques, including rule-based, decision tree, random forests, support vector machines, and semantic labeling;
• automatically correlating the extracted event types with drift detection probabilities to detect expected concept drift in the target machine learning model at a given timestamp, by a supervised classification model with event types as features and drift detection as target variables to forecast drift in real-time;
• in response to detecting the expected concept drift in the target machine learning model, automatically generating an ensemble of replacement models based on probabilities derived from a historical database of models including corresponding keys given by the event types;
• and
• automatically retraining or replacing the target machine learning model at the given timestamp at which the expected concept drift was detected.

A computer program product, the computer program product comprising:

• one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more computer-readable tangible storage medium, the program instructions executable by a processor capable of performing a method, the method comprising:
• automatically detecting features and variables considered by a target machine learning model, wherein concept drift detection includes one or more of Local Interpretable Model-Agnostic Explanations (LIME), and Shapley Additive ex-Planations (SHAP);
• automatically storing and updating a configurable corpus of relevant documents pertaining to a domain of the target machine learning model, wherein the storing and updating includes processing by annotating, splitting, and modifying of format, based on the domain of the target machine learning model;
• automatically extracting event types and corresponding time stamps from the configurable corpus of relevant documents, by natural language processing techniques, including rule-based, decision tree, random forests, support vector machines, and semantic labeling;
• automatically correlating the extracted event types with drift detection probabilities to detect expected concept drift in the target machine learning model at a given timestamp, by a supervised classification model with event types as features and drift detection as target variables to forecast drift in real-time;
• in response to detecting the expected concept drift in the target machine learning model, automatically generating an ensemble of replacement models based on probabilities derived from a historical database of models including corresponding keys given by the event types;
• and
• automatically retraining or replacing the target machine learning model at the given timestamp at which the expected concept drift was detected.