Prediction of suitable human resource for replacement in skilled job positions using Supervised Machine Learning

Skilled workers are recognized as the most important resource of a developing nation. Skills are attained by continuous learning and years of experience. The central problem of any industry in recent days is to fill the gap when a highly skilled worker switches job to a new company. This paper examines how machine learning algorithms can be used to predict whether a candidate is suitable to fill an identified skill gap, using the quantitative historical data about the skills of the workers. The problem being analyzed in this paper is the identification of a suitable replacement for a football player who has moved from a club to another. This paper provides a solution using machine learning models. Paper compares the performance of a set of machine learning algorithms and the best model to do this prediction is identified as Linear Discriminant Analysis Algorithm. The paper describes the results of the analysis of different machine learning models and illustrates how the number of classes in the feature being predicted affects the accuracy of the models used for classification. It also examines how the accuracy of the models are affected by the number features selected.