共计 1373 个字符，预计需要花费 4 分钟才能阅读完成。
UCONN FNCE 5352
Consumer Credit Project
Overview
Banks play a crucial role in market economies. They decide who can get finance and on what terms and
can make or break investment decisions. For markets and society to function, individuals and companies
need access to credit.
Credit scoring algorithms, which make a guess at the probability of default, are the method banks use to
determine whether or not a loan should be granted. This assignment requires students to improve on
the state of the art in credit scoring, by predicting the probability that somebody will experience
financial distress in the next two years.
The goal of this assignment is to build a model that borrowers can use to help make the best financial
decisions.
Files
Files have been posted to
https://github.com/mattmcd71/…
• DataDictionary.xls – Excel Spreadsheet with description of the data in the test and train files
• ConsumerCred-train.csv – Training data set. This file includes the dependent variable
SeriousDlqin2yrs, as well as the independent variables described in the data dictionary.
• ConsumerCred-test.csv – This is the dataset that you’ll need to predict outcomes for. It does not
include the dependent variable (SeriousDlqin2yrs).
• SampleSubmission.csv – This file is a sample of the file that students will need to submit.
Guidelines
Students can form teams to work on building the model. Each team must submit one or more file
submissions with the probability predictions on the test dataset. Submissions must be emailed to
Tianjiao Zhang. Submissions will be assessed on the AUC (Area under the curve) of the submitted
predictions.
