Εξόρυξη γνώσης σε τραπεζικά δεδομένα με τη βοήθεια του προγράμματος Weka

Μαυρομανωλάκης, Ιωάννης

Master Thesis

Author

Μαυρομανωλάκης, Ιωάννης

Date

2020-02

Abstract

The economic crisis that began in Europe in 2009 and continues to this day in Greece highlights the urgent need to monitor the risk a bank takes when giving a consumer loan or a credit card. A model that can predict timely and validly customers who will not be able to repay in the near future is a vital tool for any banking organization. Our goal is to describe and compare such models through their application to data from a Big4 Bank Department. We applied Logistic Regression, Artificial Neural Networks and Classification Trees to our data using either all variables or using only those that were considered significant after proper pretreatment. In particular, the step-by-step method of selecting variables and sensitivity analysis were used to identify the variables that play an important role in the output.

Postgraduate Studies Programme

Ψηφιακά Συστήματα και Υπηρεσίες

Department

Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών Συστημάτων

Number of pages

Language

Greek

URI

https://dione.lib.unipi.gr/xmlui/handle/unipi/12897
http://dx.doi.org/10.26267/unipi_dione/320

Collections

Τμήμα Ψηφιακών Συστημάτων

Show full item record

Except where otherwise noted, this item's license is described as
Attribution-NonCommercial-NoDerivatives 4.0 Διεθνές