| Popis: |
Straipsnyje nagrinėjami statybos projektų valdymo efektyvumo klausimai. Pateikiama statybos projektų valdymo veiksnių reikšmė ir jų įtaka projekto išlaidu kitimui. Taikant dirbtinius neuroninius tinklus, atliekamas esminių veiksnių identifikavimas ir jų įtakos įvertinimas projektų išlaidų kitimui. Siūlomas metodas įgalina realiai įvertinti projekto valdymo riziką, susijusią su konkrečiomis valdymo sąlygomis, ir nukreipti įmonių ir projektų vadovų pagrindinį dėmesį į svarbiausius valdymo sistemos klausimus. Researches and practitioners in the construction industry have displayed keen interest in studying the key success factors as related to the effective management of construction projects. Important aspects of the key success factor identification and a relative importance toward the construction budget performance arc often being discussed. The current study has developed a list of determining (actors dwelling on the results of the past research and on the opinions of experienced practitioners in construction management. Different from other earlier work, the goal of this study has been developing a practical application oriented model for risk assessment in construction management. Ulis paper presents an artificial neural network modeling methodology for the key success factor identification and for construction budget performance prediction. The historical data on project performance has been used to build a neural network model. A survey questionnaire was developed and distributed to construction management companies in Lithuania and in the United States of America. The respondents participating in the study evaluated all the 27 factors included in the list. Altogether, twelve key determining factors have been identified covering the areas related to a project manager, project team, project planning, management, and control. On the basis of these factors, a budget performance model has been developed. The established neural network model can be used during a competitive bidding process to evaluate management risk of a construction project and to predict construction budget performance. Hie model allows construction project managers to focus on the key success factors and to reduce the level of construction risk. The model can serve as a framework for further development of the construction management decision support system. |
