Ethically Responsible Machine Learning in Fintech
نویسندگان
چکیده
Rapid technological developments in the last decade have contributed to using machine learning (ML) various economic sectors. Financial institutions embraced technology and applied ML algorithms trading, portfolio management, investment advising. Large-scale automation capabilities cost savings make attractive for personal corporate finance applications. Using applications raises ethical issues that need be carefully examined. We engage a group of experts ethics evaluate relationship between principles ML. The paper compares experts’ findings with results obtained natural language processing (NLP) transformer models, given their ability capture semantic text similarity. reveal integrity fairness most significant relationships ethics. study includes use case SHapley Additive exPlanations (SHAP) Microsoft Responsible AI Widgets explainability tools error analysis visualization models. It analyzes credit card approval data demonstrate can address fintech, improve transparency, thereby increasing overall trustworthiness show both humans machines could err approving requests despite best judgment based on available information. Hence, human-machine collaboration contribute improved decision-making finance. propose conceptual framework addressing challenges fintech such as bias, discrimination, differential pricing, conflict interest, protection.
منابع مشابه
How to avoid ethically relevant Machine Consciousness
– This paper discusses the root cause of systems perceiving the self experience and how to exploit adaptive and learning features without introducing ethically problematic system properties. s a practical engineer one has very rarely to deal with ethic or moral impacts of machine consciousness as designed products contain only very weak forms of it [1]. However, more and more times I was asked ...
متن کاملMachine learning algorithms in air quality modeling
Modern studies in the field of environment science and engineering show that deterministic models struggle to capture the relationship between the concentration of atmospheric pollutants and their emission sources. The recent advances in statistical modeling based on machine learning approaches have emerged as solution to tackle these issues. It is a fact that, input variable type largely affec...
متن کاملFinTech and cloud in banking
The use of technologies in financial services is not new. Financial institutions have, for a long time, been implementing technological solutions to support the provision of services to their customers and to ensure compliance with their regulatory obligations. They have also long relied on outsourcing arrangements with external service providers for the provision of technological solutions. Ho...
متن کاملEmotion Detection in Persian Text; A Machine Learning Model
This study aimed to develop a computational model for recognition of emotion in Persian text as a supervised machine learning problem. We considered Pluthchik emotion model as supervised learning criteria and Support Vector Machine (SVM) as baseline classifier. We also used NRC lexicon and contextual features as training data and components of the model. One hundred selected texts including pol...
متن کاملذخیره 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: IEEE Access
سال: 2022
ISSN: ['2169-3536']
DOI: https://doi.org/10.1109/access.2022.3202889