Interactive Expert System for Budgeting World Bank Consultancy Projects: Fid-Bau Portal

Interactive Expert System for Budgeting World Bank Consultancy Projects

Rafat, Y. / Ezeldin, S.

Cost estimating is a key component of the budgeting of any project, conventional approaches may result in uncertainty and usually do not utilize the knowledge of past projects. Ideally, performing cost estimation under the best predictions of the relevant future conditions is the best approach of economic analysis to evaluate the optimum value for money. With the rise of Artificial Intelligence techniques, there are several Machine Learning (ML) methods that are being studied to capitalize on accuracy gains with regards to cost estimating techniques during the tendering phase. This research aims at developing an expert system that determines the rough order of magnitude for budgeting with an expected range of 30–35% leeway, to forecast the budget of consultancy services of World Bank projects through regression by classification using the Ensemble method. The expert system utilizes advanced ML methods to be able to generate accurate forecasts based on a rigorous database of past projects. The model was trained to identify the influential factors that affect the cost of the services in accordance with the published data related to the project and contract award. Among the studied variables are; sector, procurement method, environmental category, procurement type, region, and overall project budget. The dataset was used as inputs for over 80,000 consultancy contracts globally over the last 14 years. A web interface was then created where the cost estimates of consultancy services tendered by the World Bank are determined. The model developed showed a 72% acceptance rate in terms of model accuracy.