Prediction of Unemployment and Solutions from Labour Force

Abstract

The major aim of this research is to forecast the unemployment using the Labor force dataset. At present, unemployment is a critical problem in Sri Lanka .Government is still searching the specific solutions or reasons for the unemployment. According to the Census and Statistics Department unemployed means, Persons available and/or looking for work, and who did not work and taken steps to find a job during last four weeks and ready to accept a job given a work opportunity within next two weeks are said to be unemployed. Since unemployment is a majorfactor in determining how healthy an economy is, predicting the employability is very useful for the economy of the country. It is very useful to predict the employability or unemployability of a person with respect to the valuable crieterias to make solutions for the unemployment. In this research it is going to present a basic approach, taken for predict the unemployment and comparing the statistical approach and Artificial Neural Network to predict the unemployment. The research was performed with the idea of identifying the most efficient and effective method among above two .The prediction power was measured using the ANN and the Logistic regression on training and testing dataset of the Labor force. Three different training algorithms were used to train ANN containing a single hidden layer of ten nodes to compare the performance. The Artificial neural network designed using the Matlab and Logistic regression was performed using the R studio. Artificial neural network created using the Matlab was connected to the Visual studio to show the results.