Prediction of the development cost of commercial aviation aircraft

Abstract

Purpose The purpose of this paper is to develop a flexible design-oriented development cost method for commercial aviation aircraft based on small sample and poor information. Design/methodology/approach To predict the development cost of commercial aviation aircraft accurately, the methodology is based on the collected cost data and actual technical, and then the cost prediction relationships derived from an exhaustive statistical and filtered from regression analysis are incorporated. A series of regression equations with high regression coefficient are yielded after the cost driving factors of the development cost are fixed. Next, several sets of equations with high regression coefficient are selected for final integration. It is a flexible method that can be used efficiently to predict the cost of commercial aviation aircraft. Findings The development of commercial aviation aircraft has relatively a late start and no cost prediction model has been suitable for small sample, the proposed method is expected and is rather desirable. Practical implications By comparing the approach with the ordinary regression model and back propagation (BP) neural network, the scheme in this work is more efficient and convenient. Originality/value The results obtained in this paper show that the proposed method not only has a certain degree of versatility, but also can provide a preliminary prediction of the development cost of commercial aviation aircraft.