Machine Learning in Finance Management: Case OpusCapita
Hellström, Annu (2016)
Hellström, Annu
Haaga-Helia ammattikorkeakoulu
2016
All rights reserved
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2016090714078
https://urn.fi/URN:NBN:fi:amk-2016090714078
Tiivistelmä
This Bachelor’s thesis presents a project commissioned by OpusCapita to create an algorithm to detect anomalies, errors or fraud in corporate payment data. The main goal of this thesis is to introduce the reader to machine learning and tell about the role and tasks of finance management students in the project.
The project was conducted with a group of IT students and two finance management students. The project took place in the spring of 2016. The purpose of the project was to create an algorithm that the client could then develop into a working tool for their international customers. The purpose of the product is to alert the user about errors and frauds in their out-going payments so that they can then be checked manually.
This thesis is divided into three parts: a theoretical framework, project plan and project implementation. The theoretical part of this thesis concentrates on machine learning and the accounts payable process. The project plan part explains how the project was planned and how it was meant to be implemented at the beginning. It also explains the role of financial management students in the project. The project implementation part explains the phases of the project and how the financial management students’ tasks in the project were carried out during the phases. At the end of this thesis the conclusion of the project is explained and the project is evaluated. The reflection part of this thesis offers ideas for future development of the algorithm from the finance management student’s point of view.
The approach for this thesis is practice based. The products from finance management students were used as learning material for the IT students.
The project was conducted with a group of IT students and two finance management students. The project took place in the spring of 2016. The purpose of the project was to create an algorithm that the client could then develop into a working tool for their international customers. The purpose of the product is to alert the user about errors and frauds in their out-going payments so that they can then be checked manually.
This thesis is divided into three parts: a theoretical framework, project plan and project implementation. The theoretical part of this thesis concentrates on machine learning and the accounts payable process. The project plan part explains how the project was planned and how it was meant to be implemented at the beginning. It also explains the role of financial management students in the project. The project implementation part explains the phases of the project and how the financial management students’ tasks in the project were carried out during the phases. At the end of this thesis the conclusion of the project is explained and the project is evaluated. The reflection part of this thesis offers ideas for future development of the algorithm from the finance management student’s point of view.
The approach for this thesis is practice based. The products from finance management students were used as learning material for the IT students.