Aircraft Maintenance Budget Forecasting by Using Least Squares Method: a Case Study of Saudia Airlines
Year: 2025
Type: article
Abstract: This research aims to enhance the accuracy of aircraft maintenance budget forecasting for Saudi Airlines bydeveloping a predictive model using the Least Squares Error (LSE) approach. The study focuses on forecastingbudget allocations for engines, APUs, landing gears, and heavy checks over the period of 2025–2027. Managingmaintenance budgets presents significant challenges due to fluctuating costs, leading to inefficiencies infinancial planning, resource allocation, and operational scheduling. These fluctuations can result in increasedfinancial risk, suboptimal budget utilization, and potential disruptions in maintenance cycles. The researchemploys three forecasting models: Moving Average, Exponential Smoothing, and ARIMA, to develop a datadriven budgeting framework. The primary objectives are to improve forecasting accuracy, strengthen costcontrol measures, and evaluate model effectiveness. Historical maintenance expenditure data from 2019 to 2024were analyzed using Excel and Minitab, and predictive modeling techniques were applied to refine budgetestimations. The methodology encompasses data preprocessing, model selection and validation, performancebenchmarking, and graphical representation of forecasting outcomes. The results demonstrate varying degreesof model performance, with relatively high error rates across all methods. As a result, the study recommendstransitioning from conventional statistical forecasting models to event-based forecasting methods, which mayprovide a more reliable approach given the dynamic nature of the aviation industry. By establishing a systematicand data-driven forecasting framework, this study supports Saudi Airlines in achieving greater financial stabilityand strategic foresight in maintenance budget management. The findings contribute to broader advancements inpredictive analytics and cost optimization strategies within the aviation sector
Author: Mohamed Taha H Saeed, Prof. Mohammed Balubaid
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7077490364
FWCI:
Cites:
Cited by:
Related to: