University of Twente Student Theses
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.
|
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 |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page