Abstract

Irregularity in spare parts demand has been a recurring problem in many critical industries. The same problem is found in Dubai's water pumping stations, where demand is highly intermittent, with long periods of no usage followed by sudden increases. These irregularities are usually caused by maintenance activities or equipment failures. Forecasting such demand is challenging, as irregular patterns can lead to stockouts or overstocking. In this research, a machine learning (ML) forecasting framework is developed to handle intermittent demand for electrical spare parts in Dubai's pumping stations. The framework includes demand classification and prioritization, as well as the application of both traditional and data-driven forecasting models to generate more reliable demand estimates. The results show that although machine learning models improve performance compared to classical methods, forecasting accuracy remains limited due to the highly intermittent and sparse nature of the data. The evaluation further shows that model performance varies depending on the selected error metric, particularly under sparse conditions. This reinforces the limitations of forecasting and highlights the importance of prioritization-based decision frameworks, while still supporting better spare parts availability, procurement planning, and insight into demand behaviour.

Publication Date

4-2026

Document Type

Thesis

Student Type

Graduate

Degree Name

Engineering Management (ME)

Department, Program, or Center

Mechanical Engineering

Advisor

Dua Weraikat

Advisor/Committee Member

Ayoub Hmaidi

Advisor/Committee Member

Fuat Kosanoglu

Comments

This thesis has been embargoed. The full-text will be available on or around 5/3/2027.

Campus

RIT Dubai

Download

Share

COinS