University of Twente Student Theses

Login
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.

Forecasting of Generic Long-Lead Items for Engineer-to-Order Production Using TPE-Tuned Deep Neural Networks : A Comparative Evaluation

Groot, M.J.A. de (2025) Forecasting of Generic Long-Lead Items for Engineer-to-Order Production Using TPE-Tuned Deep Neural Networks : A Comparative Evaluation.

[img] PDF
4MB
Abstract:Specialised engineer-to-order manufacturers often face excessive lead times for highly complex components. Due to low standardisation and high project variability, procurement for these Long Lead Items (LLIs) is typically customer order-driven, potentially causing delays in manufacturing. To address this issue, this study assesses the extent to which forecast-driven procurement is feasible for generic LLIs through a case study using real-world data. The performance of statistical and advanced deep learning models is evaluated on erratic and lumpy demand. Results demonstrate that the feasibility of forecasting generic LLI demand in HNL’s ETO production environment is mixed and highly dependent on the characteristics of the specific LLI. While several models achieved improved accuracy over a naive benchmark, their inability to anticipate irregular peak demands on some time series suggests that forecasting alone may not sufficiently support forecast-driven procurement.
Item Type:Essay (Master)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:30 exact sciences in general, 50 technical science in general, 58 process technology, 70 social sciences in general, 83 economics, 85 business administration, organizational science
Programme:Industrial Engineering and Management MSc (60029)
Link to this item:https://purl.utwente.nl/essays/106499
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page