University of Twente Student Theses
Ledger Category Classification in Bookkeeping: Applying Machine Learning on Dutch Invoice Data
Mesie, P. (2024) Ledger Category Classification in Bookkeeping: Applying Machine Learning on Dutch Invoice Data.
|
PDF
5MB |
| Abstract: | Bookkeeping can be a complex and time-consuming process for small companies due to the many ledger codes available. Because of this, Moneybird has created a research assignment to investigate the possibility of implementing machine learning algorithms to speed up their customers’ bookkeeping process. In this thesis, we investigate the possibility of implementing a machine learning model that predicts the correct ledger code for Dutch invoice data using textual descriptions of the invoice lines and contextual data such as the contact company name. In our reseearch, a deep neural network based on FastText embeedings achieved the highest performance and was used to implement a prototype to show how machine learning models could be implemented to suggest ledger codes to customers of the bookkeeping software. With the results and prototype, we were able to conclude that it is possible to create a machine learning classifier that can predict ledger codes based on Dutch invoice data. |
| Item Type: | Essay (Master) |
| Clients: | Moneybird, Enschede, Netherlands |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science MSc (60300) |
| Link to this item: | https://purl.utwente.nl/essays/103654 |
| 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