Comparison of data mining algorithms in predicting the results of international tenders held to select water industry consultants (for use in decision support systems)

In developing countries where the value of money is low, consultant firms are keen to participate in international tenders. Participating in international tenders requires a lot of resources (time, cost, etc.) to evaluate the project condition and prepare a suitable proposal. Predicting the outcome of these tenders is important because it can prevent the use of resources to participate in inappropriate tenders. The aim of this paper is to identify factors that affect the outcome of water industry international tenders holding for selection of consultants and compare the classification algorithms in predicting the outcome of this tenders. effective factors include Lead department, Documents delivery method, Tender Identify Method, Type of Tender, Financer, Lead Department Partner, Final Status and Project Type and Compared algorithms include Decision Tree, ID3, Chaid, K-Nearest Neighbor (KNN), Naïve Bayes and Support Vector Machine (SVM). The most accurate algorithms are 1-SVM, 2-Chaid, 3-ID3, 4-Decision Tree, 5-Naïve Bayes and 6-KNN. so It is suggested to use the SVM algorithm as the processor in decision support systems to improve the bid/no-bid decision for consultant firms seeking to participate in the water industry international tenders.