en English is Íslenska

Thesis (Bachelor's)

Reykjavík University > Tæknisvið / School of Technology > BSc Tölvunarfræðideild / Department of Computer Science >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1946/35728

Title: 
  • Machine learning model for predicting the collection of debts
Degree: 
  • Bachelor's
Abstract: 
  • Creditinfo collects information about claims that go through their claim collection system. The goal of the project is to create a predictive model that allows users of Creditinfo’s claim collection system to plan ahead and focus on the claims that are most likely to be paid in the near future. The first part of the project was to find out which machine learning algorithms fit this project best, and then examine them further. Since the dataset includes a lot of data, there is also a need to reduce the dimensionality of the dataset, without decreasing the accuracy of the predictive model and to find those features that have the most predictive power of whether the claim will be collected. The deliverables of the project can then be used to implement the machine learning model as a part of Creditinfo’s claim collection system by Creditinfo’s employees, but Creditinfo is using similar machine learning methods in their credit rating system.

Accepted: 
  • May 28, 2020
URI: 
  • http://hdl.handle.net/1946/35728


Files in This Item:
Filename Size VisibilityDescriptionFormat 
Machine Learning Model for Predicting the Collection of Debts - H1.pdf2.2 MBLocked Until...2030/01/01Complete TextPDF
nokkvibeidni.pdf330.95 kBOpenBeiðni um lokunPDFView/Open