Machine learning based trajectory prediction to support demand forecasting: A Transformer Neural Network Approach

Air traffic sector demand and capacity balancing is an important process to enable safe and efficient flight execution. In current operations, demand and capacity are determined based on schedules and flight plans. In reality, disruptions to flights create a different situation that may not have been anticipated by the Air Navigation Service...

Two phase implementation of a machine learning (ML) model in demand forecasting for organisations

Demand forecasting plays a critical role in organizational planning, encompassing inventory management, capacity allocation, and financial decision-making. However, achieving accurate forecasts can be challenging, particularly in industries characterized by high demand volatility, such as semiconductor assembly equipment manufacturing,...

Kiosk Strategic Demand Forecasting with Scenario Planning: A case study at SITA

SITA is the world’s leading specialist in air transport communications and information technology which works with around 400 air transport members and has 2800 customers in 190 countries. TS6 kiosk is the newest generation of its kiosk family and is facing a complicated situation now. Usually, the production of a kiosk is using make-to-order...

Design, Development, and Implementationof a Demand Forecast Model: A case Study to Improve Cargill’s Demand Management

This thesis project studied the demand planning process of Cargill Global Edible Oil Solutions (GEOS) in the EMEA region and had the objective of developing a demand forecast model for the Retail Food Services customers to improve their satisfaction levels. The scope of this covered the commercial and contractual relationships, for the delivery...

Post-pandemic office real estate: A pilot study of using scenario planning to develop scenarios with quantitative office space demand for corporate real estate

The influence of the COVID-19 pandemic is profound and enduring to the entire world. A ‘recovery’ to go back in time is unlikely to happen due to the lack of uncertainty in the future. The darkest time will eventually pass, whereas post-pandemic, the era in which the pandemic is perceived to have subsided, can still accelerate existing trends...

Privacy-Preserving Techniques for Machine Learning Applications in Supply Chains

Supply chains are vital to the global economy, and so, increasing efficiency in supply chain management is of utmost importance. Modernizing technology has allowed for various uses of machine learning to be possible in several aspects of supply chains, specifically in demand forecasting with prediction models, and customer relations with chat...

Forecasting spare parts of free-floating shared vehicles: A search to a data driven approach to improve the availability of spare parts

For the shared mobility service providers, it is essential to have an economic operation and therefore, it is necessary to maximise their fleet utilisation. Of influence on the latter is the availability of the spare parts. The topics for which spare part forecasting research is already performed are different in several ways compared to the...

Dynamic human resource management decision support model based on tactical aircraft maintenance demand forecasts

The long and therefore expensive training of aircraft maintenance technicians underline the need for accurate demand forecasts that allow for dynamic control of acquisition and training rate of personnel. This control enables human resource management to react swiftly to increases in workforce demand at times of technician shortages. To help...

Investigation of active learning techniques for dynamic Time-of-Use (dToU) tariff policy design for residential users

The active learning approach is a special case of semi-supervised machine learning which is able to interactively query the user to reduce the uncertainty of the machine learning model. The approach is useful to minimize the data labeling cost. The project aims to study and use this method to characterize residential electricity users’ demand...

Behavioural Classification of Passengers in an Airport Terminal

Given the observable characteristics of a passenger in an airport, is it possible to predict their behaviour? This thesis researches the possibilities for finding behavioural classes that can help predict passenger behaviour in a passenger demand forecast (PDF) system that is developed for the European PASSME project. The thesis introduces a...

Towards more predicted and planned spare parts management: Designing an integrated approach with a focus on demand forecasting, inventory control and supply management

Service logistics companies aim for their high value capital assets to be operationally available, to prevent lost revenues and customer dissatisfaction. To assure this maintenance is performed, and therefore spare parts are required. An important activity is to have spare parts available when they are demanded for conducting maintenance....

Interval Forecasting for Airline Passenger Demand: An Application to Airline Network Development

In the past forty years, the volume of air travel has increased tenfold. While demand growth for OECD markets has slowed down in recent years, there is still a potential for markets where air services are currently not provided. It is the goal of the airline network development process to locate these potentially profitable markets. One of the...

Performance Impact of Improved Departure Time Prediction Relative to Sector Demand & Arrival Time Predictability

This thesis deals with traffic forecasts of Airspace Users for Air Navigation Service Providers. Currently there is a high amount of uncertainty in the traffic forecast. Air Traffic Flow Managers anticipate for unforeseen traffic by increasing the forecasted maximum capacity threshold by more than 10%. The European ATM research program SESAR...

Long term planning for the water supply system of the Metropolitan Area of Amsterdam under new water saving regimes of the retail customers: Understanding the system and addressing uncertainties

The centralized drinking water supply system of the Metropolitan Area of Amsterdam, operated and owned mainly by Waternet, has high performance indicators and satisfies the full demand for water in the urban grid and surrounding areas on a full cost recovery basis. Social and technological developments, stemming mainly from (i) the increasing...

Spare Parts Demand Categorisation in the Defence Material Organization: Assessing the applicability and effectiveness of theoretical categorization schemes and statistical demand forecasting methods in a real-world setting of weapons systems related spare parts demand

In this thesis the current inventory control at the Defence Material Organisation is analysed in light of the pending implementation of the SAP-ECC/DFPS ERP-system for demand forecasting and inventory control. The scope for this research has been set on the demand forecasting of weapon systems related spare parts under training and peace-time...