Predictive modeling method and system for dynamically quantifying employee growth opportunity

A machine learning predictive modeling system, comprising:

• a computer system;
• one or more processors running on the computer system, wherein the one or more processors are configured to execute program instructions to cause the computer system to:
• aggregate sample data regarding a plurality of metrics associated with employee growth opportunity and voluntary employee turnover, wherein the sample data is specific to employers that use dynamic predictive modeling of employee satisfaction and retention;
• scrub sample data by removing incomplete data or data with little predictive value;
• perform iterative analysis based on machine learning with a training data split from the sample data to construct a predictive model, wherein the machine learning comprises at least one of supervised learning, unsupervised learning, and reinforcement learning;
• test an accuracy of the predictive model with a test data split from the sample data;
• in response to an error rate above a predetermined threshold between the training and test data that is determined after the testing:
• control how fast the model learns patterns and which patterns to identify and analyze by changing one or more hyper-parameters of the predictive model;
• randomize the training data and the test data;
• repeat the iterative analysis based on the machine learning with the training data to construct the predictive model;
• and
• re-test the accuracy of the predictive model;
• determine, using predictive model, for each individual of a plurality of individuals, a predicted voluntary employee turnover for each individual based on metrics associated with employee growth opportunity;
• convert the predicted voluntary employee turnover for a plurality of selected employers into an index of voluntary employee turnover based on the predicted voluntary employee turnover relative to an observed voluntary employee turnover for employers with similar employee growth opportunities;
• and
• rank order the plurality of selected employers according to the index of voluntary employee turnover for each employer.

A computer program product for machine learning predictive modeling, the computer program product comprising:

• a non-transitory computer-readable storage media having program instructions embodied thereon to perform the steps of:
• aggregating sample data regarding a plurality of metrics associated with employee growth opportunity and voluntary employee turnover, wherein the sample data is specific to employers that use dynamic predictive modeling of employee satisfaction and retention;
• scrubbing sample data by removing incomplete data or data with little predictive value;
• performing iterative analysis based on machine learning with a training data split from the sample data to construct a predictive model, wherein the machine learning comprises at least one supervised learning, unsupervised learning, and reinforcement learning;
• testing an accuracy of the predictive model with a test data split from the sample data,
• in response to an error rate above a predetermined threshold between the training and test data that is determined after the testing:
• controlling, by one or more processor, how fast the model learns patterns and which patterns to identify and analyze by changing one or more hyper-parameters of the predictive model;
• controlling, by one or more processor, how fast the model learns patterns and which patterns to identify and analyze by changing one or more hyper-parameters of the predictive model;
• controlling, by one or more processor, how fast the model learns patterns and which patterns to identify and analyze by changing one or more hyper-parameters of the predictive model;
• randomizing the training data and the test data;
• repeating the iterative analysis based on the machine learning with the training data to construct the predictive model;
• and
• re-testing the accuracy of the predictive model;
• determining, using predictive model, for each individual of a plurality of individuals, a predicted voluntary employee turnover for each individual based on metrics associated with employee growth opportunity;
• converting the predicted voluntary employee turnover for a plurality of selected employers into an index of voluntary employee turnover based on the predicted voluntary employee turnover relative to an observed voluntary employee turnover for employers with similar employee growth opportunities;
• and
• ranking the plurality of selected employers according to the index of voluntary employee turnover for each employer.