Computer-based systems, computing components and computing objects configured to implement dynamic outlier bias reduction in machine learning models

A method comprising:

• receiving, by at least one processor a well drilling training data set comprising a plurality of well drilling data records;
• wherein each well drilling data record comprises:
• at least one independent variable associated with well drilling parameters of at least one drilling run, and
• a target variable representing at least one non-productive time performance metric associated with the at least one drilling run;
• and
• determining, by the at least one processor, at least one bias criteria;
• selecting, by the at least one processor, at least one well drilling performance machine learning model based at least in part on the well drilling performance model request;
• iteratively refining, by the at least one processor, a set of model parameters of the at least one well drilling performance machine learning model until a termination criterion is met, comprising:
• determining an outlier data set and a non-outlier data set associated with the well drilling training data set based at least in part on:
• an error calculation between each model predicted value relative to each target value of the well drilling training data set, and
• the at least one bias criteria;
• and
• updating the set of model parameters based at least in part on at least one of:
• the non-outlier data set, or
• the outlier data set;
• outputting, by the at least one processor, a production-ready well drilling performance machine learning model of the at least one well drilling performance machine learning model comprising the set of model parameters.