# Possibility Theory Quantification in Human Capital Management: A Scientific Machine Learning (SciML) Perspective

**Authors:** Barbara Keary, Karriem "A. J. " Perry  
**arXiv:** [2302.14088](https://arxiv.org/abs/2302.14088)  
**Date:** 2023-02-27  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2302.14088v3/

## Key points

- The study explores the use of Machine Learning (ML) in Human Capital Management (HCM)
- The approach used is employing partial differential equations (PDEs) to address the complexity of anthropomorphic systems
- Scientific Machine Learning (SciML) is used to quantify possibility theory in HCM
- The mathematical representation offers a robust evaluation of human activities and demonstrates the potential of Bayesian-based machine learning techniques for visual representation in predictive analytics applications
- Linear regression analysis shows that there is a statistically significant relationship between targeted productivity and date, supporting hypotheses H2b and H1b
- This study contributes to advancing our understanding of how SciML can be used to address complex problems in HRM/HCM by quantifying possibility theory
- It highlights how ML techniques can be employed for visual representation in predictive analytics applications.

## Summary

This preprint manuscript explores the use of Machine Learning (ML) in Human Capital Management (HCM) through a unique approach of employing partial differential equations (PDEs) to address the complexity of anthropomorphic systems. The study uses Scientific Machine Learning (SciML), which uses PDEs to represent physical systems and domain-specific data, to quantify possibility theory in HCM. The mathematical representation offers a robust evaluation of human activities and demonstrates the potential of Bayesian-based machine learning techniques for visual representation in predictive analytics applications. Using linear regression analysis with targeted productivity as the dependent variable and date as the independent variable, the results show that there is a statistically significant relationship between targeted productivity and date. This provides evidence to support hypotheses H2b and H1b, suggesting that conditions do significantly impact the relationship among covariates and that their structure changes significantly over time given a set of initial conditions. This study contributes to advancing our understanding of how SciML can be used to address complex problems in HRM/HCM by quantifying possibility theory. It also highlights how ML techniques can be employed for visual representation in predictive analytics applications.