Forecasting is a fundamental process in the project management field, since it plays a key role in the pursuit of objectives and resource-usage efficiency. Nowadays the available techniques for the estimation of a project cost involve many problems, mainly due to the low accuracy during the early phase of the project, the most critical for cost-forecasting; moreover, they provide deterministic results without considering the possibility of errors affecting input data. From this perspective a new forecasting method is here presented, with the aim of providing an available technique that is able to improve the decision-making process during the project execution phase. This method, based on the implementation of a Kalman Filter integrated into the Earned Value Management system, is able to provide probabilistic results and high accuracy-levels of prediction in the early phase of the project. This new approach has been then applied in an aeronautical project of the company Leonardo S.p.A., as part of the author’s curricular internship, in order to assess the achieved performances.
La previsione è un processo fondamentale nel campo del project management, poiché essa assume un ruolo chiave nel perseguimento degli obiettivi e dell’efficienza nell’utilizzo delle risorse. Le tecniche ad oggi esistenti per la previsione del costo finale di un progetto sono caratterizzate da una serie di problematiche, su tutte il basso livello di accuratezza delle previsioni effettuate nelle fasi iniziali del progetto, e la natura deterministica dei risultati forniti che non tiene in considerazione la possibilità di errori nei dati in input. In quest’ottica, viene qui presentato lo sviluppo di un nuovo modello previsionale in grado di ridurre tali problematiche, e di ottimizzare così i processi decisionali relativi a un progetto durante il suo avanzamento. Tale modello, basato sull’implementazione di un Filtro di Kalman integrato al sistema Earned Value Management, è in grado di fornire risultati probabilistici e alti livelli di accuratezza previsionale fin dalle fasi iniziali. Il modello è stato poi testato applicandolo in un progetto aeronautico dell’azienda Leonardo S.p.A., nell’ambito di uno stage curricolare, allo scopo di valutarne le performance.
Development of a project cost forecasting model based on the implementation of a Kalman filter integrated into the earned value management approach
Ursini, Giacomo
2019/2020
Abstract
Forecasting is a fundamental process in the project management field, since it plays a key role in the pursuit of objectives and resource-usage efficiency. Nowadays the available techniques for the estimation of a project cost involve many problems, mainly due to the low accuracy during the early phase of the project, the most critical for cost-forecasting; moreover, they provide deterministic results without considering the possibility of errors affecting input data. From this perspective a new forecasting method is here presented, with the aim of providing an available technique that is able to improve the decision-making process during the project execution phase. This method, based on the implementation of a Kalman Filter integrated into the Earned Value Management system, is able to provide probabilistic results and high accuracy-levels of prediction in the early phase of the project. This new approach has been then applied in an aeronautical project of the company Leonardo S.p.A., as part of the author’s curricular internship, in order to assess the achieved performances.File | Dimensione | Formato | |
---|---|---|---|
2021_04_Ursini.pdf
non accessibile
Dimensione
3.78 MB
Formato
Adobe PDF
|
3.78 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/174434