Algorithmic discrimination in the credit domain: what do we know about it?

نویسندگان

چکیده

Abstract The widespread usage of machine learning systems and econometric methods in the credit domain has transformed decision-making process for evaluating loan applications. Automated analysis applications diminishes subjectivity process. On other hand, since is based on past decisions recorded financial institutions’ datasets, very often consolidates existing bias prejudice against groups defined by race, sex, sexual orientation, attributes. Therefore, interest identifying, preventing, mitigating algorithmic discrimination grown exponentially many areas, such as Computer Science, Economics, Law, Social Science. We conducted a comprehensive systematic literature review to understand (1) research settings, including theory foundation, legal framework, applicable fairness metric; (2) addressed issues solutions; (3) open challenges potential future research. explored five sources: ACM Digital Library, Google Scholar, IEEE Springer Link, Scopus. Following inclusion exclusion criteria, we selected 78 papers written English published between 2017 2022. According meta-analysis this survey, been mainly looking at CS, Economics perspectives. There great topic area, especially providing access mortgage market differential treatment (different fees, number parcels, rates). Most attention devoted due dataset. Researchers are still only dealing with direct discrimination, fairness, while indirect (structural discrimination) not received same attention.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Superior Capsule Reconstruction: What Do We Know?

The management of irreparable rotator cuff tears remains challenging. Since its introduction by Mihata in 2012, superiorcapsule reconstruction (SCR) has grown in popularity at an astonishingly rapid rate. The aim of this article is to providea comprehensive review of the available literature, in order to highlight what has so far been published on SCR,covering all aspects including biomechanica...

متن کامل

Q&A: What do we know about influenza and what can we do about it?

Influenza pandemics occur when human populations are infected by a variant virus to which a population has no prior immunity. What are the crucial varying genes? The crucial genes are those encoding the two viral surface proteins hemagglutinin (H or HA) and neuraminidase (N or NA). The influenza A viruses [1] that infect mammals like us replicate principally in the epithelial cells of the airwa...

متن کامل

Molecular approaches to diagnosis of invasive aspergillosis what we know and what we do not know.

Invasive aspergillosis (IA) are a major complication in immunocompromized patients where can be serious and rapidly fatal. Early diagnosis and early appropriate antifungal treatment is important in reducing mortality and morbidity. But despite many efforts to develop detection methods, the diagnosis of IA still remains challenging and current conventional methods are limited for adequate diagno...

متن کامل

What do we know and when do we know it?

Two essential aspects of virtual screening are considered: experimental design and performance metrics. In the design of any retrospective virtual screen, choices have to be made as to the purpose of the exercise. Is the goal to compare methods? Is the interest in a particular type of target or all targets? Are we simulating a 'real-world' setting, or teasing out distinguishing features of a me...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: AI & society

سال: 2023

ISSN: ['0951-5666', '1435-5655']

DOI: https://doi.org/10.1007/s00146-023-01676-3