Metaheuristic algorithms based automated evaluation method for public investment projects

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Türkiye

Tezin Onay Tarihi: 2014

Öğrenci: TÜLUĞ FİGEN YILMAZ

Danışman: PINAR KARAGÖZ

Özet:

The public investment projects are essential to improve the state economy prosperously and to improve life of people. In spite of high need for public investment projects, resources are limited. So, there has been increased requirement on the accountability and efficiency of the public investment projects. To overcome these issues, project performance evaluation systems are needed. Scientific and reasonable performance measurement can be utilized in these systems to evaluate public investment projects. A set of measurement index and the assessment method must be developed to strengthen the measurement of public investment projects performance. In this thesis, a new project evaluation system is introduced. In attribute selection part of this model, Genetic Algorithm and several data mining methods are used. Harmony Search and Genetic Algorithm are used at building evaluation model after attribute selection. The proposed system is applied to evaluation process of 493 World Bank projects. The results are compared with the classical project evaluation technique using the Analytical Hierarchy Process and well known classification methods in the literature. Considering the evaluation results, the proposed work is more successful than these well known methods in the literature.