Human Resource Demand Prediction and Configuration Model Based on Grey Wolf Optimization and Recurrent Neural...

Area of Science:

• Business Administration
• Computer Science
• Data Science

Background:

• Effective human resources (HR) management is crucial for business development and organizational efficiency.
• Predicting human resource demand is challenging due to market immaturity, fluctuating corporate needs, and data limitations.
• Existing HR forecasting methods often struggle with nonlinearity and uncertainty stemming from multiple influencing variables.

Purpose of the Study:

• To develop and validate a novel quantitative forecasting method for predicting human resource demand.
• To address the complexities and uncertainties in HR demand prediction within a maturing labor market.
• To enable organizations to better estimate personnel needs for improved strategic planning and objective achievement.

Main Methods:

• Data collection and preprocessing, including normalization.
• Feature extraction using Principal Component Analysis (PCA).
• Development of a hybrid model combining Recurrent Neural Networks (RNNs) and Grey Wolf Optimization (GWO) for HR demand forecasting.

Main Results:

• The proposed RNN with GWO model demonstrated effective prediction of human resource needs.
• The method enhances the accuracy and adaptability of HR demand forecasting.
• Principal Component Analysis (PCA) aided in effective feature extraction for the model.

Conclusions:

• The novel RNN-GWO quantitative method offers a more relevant and adaptive approach to HR demand prediction.
• Accurate HR demand forecasting enables organizations to optimize personnel planning and achieve strategic objectives.
• This approach can assist businesses in navigating labor market fluctuations and adapting HR structures effectively.