Unit:
Κατεύθυνση Ψηφιακά Μέσα Επικοινωνίας και Περιβάλλοντα ΑλληλεπίδρασηςLibrary of the Faculties of Political Science and Public Administration, Communication and Mass Media Studies, Turkish and Modern Asian Studies, Sociology
Author:
Giannoukakou Nikoleta
Supervisors info:
Κωνσταντίνος Μουρλάς, Αναπληρωτής Καθηγητής, Τμήμα Επικοινωνίας και ΜΜΕ, ΕΚΠΑ
Αικατερίνη Σωτηράκου, Επιστημονική Συνεργάτης, Τμήμα Επικοινωνίας και ΜΜΕ, ΕΚΠΑ
Original Title:
Αποκαλύπτοντας την προκατάληψη: Μια συγκριτική ανάλυση των τεχνικών μηχανικής μάθησης στην παγκόσμια αγορά ψηφιακής τραπεζικής και οι ηθικές επιπτώσεις τους
Translated title:
Uncovering Bias: A Comparative Analysis of Machine Learning Techniques in the Global Digital Banking Market and Their Ethical Implications
Summary:
The adoption of artificial intelligence and machine learning techniques in financial institutions has transformed their traditional operations, revolutionizing both credit risk assessment and the internal processes of the institutions.
This paper performs a comparative analysis of machine learning techniques used in the global digital banking market, focusing on their predictive capabilities and ethical considerations. By examining logistic regression, decision tree and random forest algorithms, we evaluate their effectiveness in predicting financial product approval decisions, while exploring the potential biases inherent in the models.
Using a dataset from the financial sector, the impact of demographic variables, such as gender and marital status, on loan approval outcomes is analyzed. The findings reveal different levels of importance of attributes in different algorithms, highlighting the importance of interpretability and fairness in machine learning models. Through this analysis, the ethical implications of algorithmic decision making in financial services are highlighted, supporting transparent and accountable practices to mitigate bias and promote financial inclusion.
Main subject category:
Social, Political and Economic sciences
Other subject categories:
Technology - Computer science
Keywords:
Machine learning, artificial intelligence, digital banking, bias, justice, ethical implications, loan approval, accounting regression, decision trees, random forest, data set.
