Multiple Factors’ Influence on the Employees’ Performance: Analysis Based on Random Forest and Polynomial Regression

Yufei Wang

2024

Abstract

This study aims to identify and analyze key factors influencing employee performance using advanced machine learning techniques. Specifically, it seeks to elucidate the relationships between variables such as salary, employee engagement, and satisfaction, and to develop strategies for optimizing these factors to enhance performance. A dataset from Kaggle was preprocessed to ensure data quality, including the imputation of missing values and transformation of categorical features. A numerical feature pipeline was employed to impute missing values using the median method and standardize the data. For categorical features, missing values were imputed using the most common method and transformed into a binary format using OneHotEncoder. A Random Forest (RF) model was utilized to identify the most significant features, with the model’s performance optimized through GridSearchCV and resampling techniques to address class imbalance. Polynomial Regression models were subsequently employed to explore nonlinear relationships between the significant factors identified by the RF model and employee performance. The polynomial transformations of degree 3 were applied to capture nonlinearity. Each model focused on one of the top three important independent variables: salary, engagement survey scores, and employee satisfaction. Results indicate that engagement survey scores, employee satisfaction, and salary exhibit significant nonlinear relationships with performance.

Download


Paper Citation


in Harvard Style

Wang Y. (2024). Multiple Factors’ Influence on the Employees’ Performance: Analysis Based on Random Forest and Polynomial Regression. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 51-55. DOI: 10.5220/0013206200004568


in Bibtex Style

@conference{ecai24,
author={Yufei Wang},
title={Multiple Factors’ Influence on the Employees’ Performance: Analysis Based on Random Forest and Polynomial Regression},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={51-55},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013206200004568},
isbn={978-989-758-726-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - Multiple Factors’ Influence on the Employees’ Performance: Analysis Based on Random Forest and Polynomial Regression
SN - 978-989-758-726-9
AU - Wang Y.
PY - 2024
SP - 51
EP - 55
DO - 10.5220/0013206200004568
PB - SciTePress