Predictive models for Employee satisfaction and retention in HR using Machine learning
Main Article Content
Abstract
A successful organization depends on its stakeholders being satisfied and having faith in the business. A company's employees are one of its most important assets since they are essential to the general expansion and development of the company. A corporation with a much higher personnel retention rate will be deemed successful in achieving its goals. If a company loses a talented and trained employee, it may incur financial losses from the training costs of replacement hires. This is because losing an employee of that caliber could affect more than just how smoothly the company runs. This article aims to introduce a machine learning framework we created to estimate an organization's staff retention rate using a previously collected dataset. Several machine-learning techniques are applied during the model-development process. K-nearest neighbor (KNN), ensemble with boosted tree, decision tree (DT), and support vector machine (SVM) are some of these methods. The feature value types in the dataset are manually modified to meet the model's needs in order to produce a well-trained model. The model that was built in this way obtained an accuracy rating of 98%.