Vinsamlegast notið þetta auðkenni þegar þið vitnið til verksins eða tengið í það: http://hdl.handle.net/1946/35728
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.
|Machine Learning Model for Predicting the Collection of Debts - H1.pdf||2.2 MB||Lokaður til...01.01.2030||Heildartexti|
|nokkvibeidni.pdf||330.95 kB||Opinn||Beiðni um lokun||Skoða/Opna|