Obtain Employee Turnover Rate and Optimal Reduction Strategy Based On Neural Network and Reinforcement Learning

TL;DR

This paper develops a neural network model to predict employee turnover and employs reinforcement learning to generate cost-effective strategies for reducing turnover, aiming to enhance enterprise human resource management.

Contribution

It introduces a combined neural network and reinforcement learning approach to predict employee turnover and optimize reduction strategies, which is a novel integration in HR management.

Findings

The model accurately predicts employee turnover.

Reinforcement learning generates effective reduction strategies.

Strategies improve efficiency and reduce costs.

Abstract

Nowadays, human resource is an important part of various resources of enterprises. For enterprises, high-loyalty and high-quality talented persons are often the core competitiveness of enterprises. Therefore, it is of great practical significance to predict whether employees leave and reduce the turnover rate of employees. First, this paper established a multi-layer perceptron predictive model of employee turnover rate. A model based on Sarsa which is a kind of reinforcement learning algorithm is proposed to automatically generate a set of strategies to reduce the employee turnover rate. These strategies are a collection of strategies that can reduce the employee turnover rate the most and cost less from the perspective of the enterprise, and can be used as a reference plan for the enterprise to optimize the employee system. The experimental results show that the algorithm can indeed improve the efficiency and accuracy of the specific strategy.