An Effective Opinion Mining-Based K-Nearest Neighbours Algorithm for Predicting Human Resource Demand in Business

Abstract

The process of estimating and preparing for an association's future supply and management of human resources is known as human resource planning (HRP). It is a significant section of directorial development. This study suggested a novel technique to HRP demand forecasting using the Modified K-nearest neighbor (M-KNN) algorithm. M-KNN is machine learning (ML) algorithms that locate the k major comparable data sample to a new information sample and uses those data sample to forecast the value of the new sample. We generate an HR order estimate pointer organization consisting of variables that pressure HR order such as market share, sales volume, and economic conditions. We use M-KNN to find the k most similar data samples to each data point in the display organization and use those data samples to predict HR command. We assessed our M-KNN algorithm using data from a actual association and find that it can correctly forecast HR command with an fault speed of less than 5%. M-KNN is a talented advance to HRP command forecasting as it is easy to use, does not necessitate a lot of data, and can exactly predict HR command in the attendance of non-linearity and haziness.