Labor Market Forecasting by Using Data Mining

Data mining approach was used in this paper to predict labor market needs, by implementing Naive Bayes Classifiers, Decision Trees, and Decision Rules techniques. Naive Bayes technique implemented by creating tables of training; the sets of these tables were generated by using four factors that affect employee's continuity in their jobs. The training tables used to predict the classification of other (unclassified) instances, and tabulate the results of conditional and prior probabilities to test unknown instance for classification. The information obtained can classify unknown instances for employment in the labor market. In Decision Tree technique, a model was constructed from a dataset in the form of a tree, created by a process known as splitting on the value of attributes. The Decision Rules, which was constructed from Decision Trees of rules gave the best results, therefore we recommended using this method in predicting labor market. (C) 2013 The Authors. Published by Elsevier B.V. Selection and peer review under responsibility of the organizers of the 2013 International Conference on Computational Science