Application of knowledge discovery in database (KDD): techniques in cost overrun of construction project

الموضوعات

علوم تطبيقية وتكنولوجية

الملخص

Construction projects are considered successful when accomplished on estimated time as per baseline schedule and within allocated target budget. Currently cost overrun is a global challenge to successful completion of construction projects. To overcome this problem, earlier studies were performed to investigate the factors of cost overrun. As knowledge Discovery in Data (KDD) and data mining techniques have been implemented effectively in different research areas to extract novel and valuable knowledge from historical data. Similarly, in construction industry these techniques can be also applied to construction projects’ historical data if this data is captured in an organized and reliable manner. The main purpose of this research is to develop a model that predicts project’s cost overrun category using a suitable data mining technique, the proposed model will utilize the cost overrun factors as predictors. A comprehensive literature review was performed to detect the main factors of cost overrun. This analysis resulted in nominating twelve factors that can be easily measured and analyzed at construction projects. After that, a data acquisition model is developed to capture the relevant historical data and metadata from executed construction projects in a consistent data warehouse. The developed data warehouse would enable the application of KDD and data mining techniques to tackle cost overrun problem. A case study was performed to validate the proposed model by utilizing actual data set for executed projects which was obtained from a government organization. Several data mining techniques for clustering and classification of data points were tested and used. The resulted model is simple, interpretable and has good prediction accuracy 60.87٥/o. The research provides significant contribution in different three aspects which are: implementing a full KDD model, utilizing twelve cost overrun factors as model predictors and applying three steps of data mining in series which are clustering, feature selection for predictors and classification. It was found that all these steps are showing good improvement in the performance of the prediction model. Construction companies can use the model to identify the occurrence of cost overrun at the early stages ofthe project and attempt to avoid it by providing sufficient funds.

روابط وملفات

التعريف والنوع

رقم الوثيقة

0b17ae5d-622b-4850-9396-5bdd02f4992f

رقم العقد

0

نوع الوسائط

Crawler

نوع المحتوى

الرسائل العلمية

صيغة المصدر

رسائل ماجيستير

نوع الملف

pdf text

أسماء الملفات

0b17ae5d-622b-4850-9396-5bdd02f4992f_1.pdf

بيانات النشر

ألقاب المؤلفين

[{"name_ar":"Ahmed Mohamed Hammad","title_ar":"اشراف","title_en":"Supervision"},{"name_ar":"Mai M. M. Ghazal","title_ar":"اعداد","title_en":"Preparation"}]

اللغة

English

المصدر والدورية

اسم المصدر

Application of knowledge discovery in database (KDD): techniques in cost overrun of construction project

المحتوى والصفحات

عدد الصفحات

0

كلمات الباحثين

Construction management, Construction projects, Cost overrun, Cost performance, Data mining, Data warehousing, Knowledge discovery, Knowledge management.

إشراف وإعداد

الإشراف

Ahmed Mohamed Hammad

الإعداد

Mai M. M. Ghazal

الاقتباسات الببليوغرافية