Ανάλυση πιστωτικού κινδύνου μέσω μεθόδου μηχανικής μάθησης
View/
Keywords
Εξόρυξη γνώσης ; Μηχανική μάθηση ; Πιστωτικός κίνδυνος ; Πρόβλεψη ; Πιθανότητα αθέτησης ; Αξιολόγηση πιστωτικού κινδύνου ; Δέντρα απόφασηςAbstract
The rapid development of technology, the competitive environment and the huge amount of data available today, take into account the urgent need of companies to move to a new digital reality. The use of data to automate processes and decisions through the use of new methods such as artificial intelligence and machine learning is a major goal of organizations. In its first steps, Artificial Intelligence, although it aroused excitement and interest, could not be implemented with the expected success. Recent technological developments and discoveries have made Artificial Intelligence applications commercially viable. Artificial Intelligence is becoming one of the most popular technologies that is going to transform the banking industry, as its applications prove to be viable and their acceptance by customers satisfactory.
In the banking industry, Artificial Intelligence is applied, among other things, to customer service, fraud detection and money laundering, regulatory compliance, credit risk analysis and assessment. In this dissertation, three models of supervised machine learning were developed, which classify the customers of a bank into ”good” or ”bad” based on the possibility of default.
The algorithms used are Random Forest,KNN and Decision Trees.
Postgraduate Studies Programme
Πληροφοριακά Συστήματα και ΥπηρεσίεςDepartment
Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών ΣυστημάτωνNumber of pages
56Language
GreekCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα