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.

Dynamic predictive cycle counting based on imperfect information in the spice industry

Hordijk, Thomas (2023) Dynamic predictive cycle counting based on imperfect information in the spice industry.

[img] PDF
4MB
Abstract:Euroma is one of the largest companies partaking in the global spice and herb industry. The main facility in Zwolle mixes a million kilograms of spice and herb blends every week. The material volume and the number of inventory transactions is immense and prone to errors. The high throughput makes traditional counting approaches unsuitable. This thesis proposes a model that uses machine learning to make better cycle count decision. The machine learning models that are investigated are the following regression models: Ridge, Bayesian Ridge, Lasso, Decision Tree, Random Forest, XGBoost, and Neural Network. The proposed solution is compared to traditional cycle count models using a Monte Carlo simulation. The traditional models that were used are ABC Classification, transaction-, location-based and random cycle counting. Experiments showed that a Random Forest Regression based cycle counting approach outperformed most traditional counting methods, equaling transaction-based.
Item Type:Essay (Master)
Clients:
Euroma, Zwolle, Netherlands
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:85 business administration, organizational science
Programme:Industrial Engineering and Management MSc (60029)
Link to this item:https://purl.utwente.nl/essays/97417
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page