923 Hits in 5.6 sec

Algorithmic Fairness in Mortgage Lending: from Absolute Conditions to Relational Trade-offs

Michelle Seng Ah Lee, Luciano Floridi
2020 Minds and Machines  
We introduce a new approach that considers fairness-not as a binary, absolute mathematical condition-but rather, as a relational notion in comparison to alternative decisionmaking processes.  ...  Each of these notions is often presented as a one-size-fits-all, absolute condition; however, in reality, the practical and ethical trade-offs are unavoidable and more complex.  ...  The US mortgage data are used to demonstrate a new methodology that views fairness as a trade-off of objectives-not as an absolute mathematical condition-but in relation to an alternative decisionmaking  ... 
doi:10.1007/s11023-020-09529-4 fatcat:2okzjxh7xjf3hi66tjmr5dticq

Counterfactual Fairness in Mortgage Lending via Matching and Randomization [article]

Sama Ghoba, Nathan Colaner
2021 arXiv   pre-print
In our work, we use the framework of counterfactual fairness to train fair machine learning models.  ...  Unfairness in mortgage lending has created generational inequality among racial and ethnic groups in the US.  ...  Counterfactual fairness. In NeurIPS. Lee, M. S. A. and Floridi, L. (2021). Algorithmic fairness in mortgage lending: from absolute conditions to relational trade-offs.  ... 
arXiv:2112.02170v1 fatcat:pk7euv3qrnf5vh6hvaha2nuqkq

The CRA Implications of Predatory Lending

Kathleen C. Engel, Patricia A. McCoy
2002 Social Science Research Network  
The article concludes that the CRA should be used to penalize lenders that engage in predatory lending and recommends that federal bank regulators use CRA to sanction behavior that could encourage further  ...  This article considers the Community Reinvestment Act's role in combating predatory lending.  ...  In the interim, the Federal Trade Commission had sued Associates and Citigroup for predatory lending abuses under the Federal Trade Commission Act. 92 In the EAB decision, in contrast with its prior  ... 
doi:10.2139/ssrn.315103 fatcat:abdaydyfkvb4rgnsxj7ojlkbzq

The Attractions and Perils of Flexible Mortgage Lending

Mark J. Garmaise
2013 The Review of financial studies  
Abstract A mortgage program that offered borrowers greater flexibility in the timing of repayments increased a bank's volume by over 35%. Loans in the program exhibited superior performance.  ...  Despite this, a regression discontinuity analysis shows that the causal impact of offering flexibility was to attract borrowers to the bank who experienced quadruple the average delinquency rate.  ...  Nonetheless, in setting the rate premium on Flexible loans, the bank did likely face a trade off between profitability per mortgage and volume. 5 4 As an example, consider a Flexible mortgage of $369,550  ... 
doi:10.1093/rfs/hht050 fatcat:ziou3dwbfnfbzabq4jt3rdwxo4

The Misregulation of Person-to-Person Lending

Andrew Verstein
2011 Social Science Research Network  
Technological and financial innovation allows person-to-person ("P2P") lending to connect lenders and borrowers in inspiring ways never before imagined. However, all is not well with P2P lending.  ...  The SEC's misregulation of P2P lending provides an opportunity to theorize about regulation in a rapidly disintermediating world.  ...  prohibition against off-market trading.  ... 
doi:10.2139/ssrn.1823763 fatcat:wbohp3ew4jfphatyllxogg7f3y

Restrictions on Credit: A Public Policy Analysis of Payday Lending

Petru Stelian Stoianovici, Michael T. Maloney
2008 Social Science Research Network  
I capture the intensity of the payday lending activity in a state by the number of payday lending stores.  ...  Using state level data between 1990 and 2006, I find no empirical evidence that payday lending leads to more bankruptcy filings, which casts some doubt on the debt trap argument against payday lending.  ...  Restrictions on payday lending could stop or discourage people in this group from engaging in voluntary trade, and could force them to choose a less preferred alternative (presumably more costly). b) It  ... 
doi:10.2139/ssrn.1291278 fatcat:uhxwhxbulrfltpiptxxuytywti

Default or profit scoring credit systems? Evidence from European and US peer-to-peer lending markets

Štefan Lyócsa, Petra Vašaničová, Branka Hadji Misheva, Marko Dávid Vateha
2022 Financial Innovation  
To validate our profit scoring models with traditional credit scoring models, we use data from a European P2P lending market, Bondora, and also a random sample of loans from the Lending Club P2P lending  ...  AbstractFor the emerging peer-to-peer (P2P) lending markets to survive, they need to employ credit-risk management practices such that an investor base is profitable in the long run.  ...  ) used data from Bondora. fair comparison across markets and validate our PS models, we also use a random sample of loans from the Lending Club marketplace.  ... 
doi:10.1186/s40854-022-00338-5 fatcat:dmstpmh2zbelzlnhkyvat4nelu

Marketplace Lending as a New Means of Raising Capital in the Internal Market: True Disintermediation or Reintermediation? [chapter]

Eugenia Macchiavello, Antonella Sciarrone Alibrandi
2021 Digital Finance in Europe: Law, Regulation, and Governance  
The infor- mation and factors that ECSPs are required to consider in such an assessment to ensure price fairness, as well as the related minimum governance and organiza- tional requirements, will be further  ...  The crucial question relates, in fact, to whether market- place lending represents – as originally described by actors in the sector, espe- cially in contractual agreements by means of disclaimers – a  ... 
doi:10.1515/9783110749472-003 fatcat:x7ejhuhfd5emhdz7metasvapjy

Formalising trade-offs beyond algorithmic fairness: lessons from ethical philosophy and welfare economics

Michelle Seng Ah Lee, Luciano Floridi, Jatinder Singh
2021 AI and Ethics  
In this paper, we derive lessons from ethical philosophy and welfare economics as they relate to the contextual factors relevant for fairness.  ...  Scholars have responded by introducing numerous mathematical definitions of fairness to test the algorithm, many of which are in conflict with one another.  ...  In addition, fairness should not be considered in isolation from the related ethical goals.  ... 
doi:10.1007/s43681-021-00067-y fatcat:bo72yzwgvvfwxjrtv4iduuglq4

'On the Take': The Black Box of Credit Scoring and Mortgage Discrimination

Cassandra Havard
2010 Social Science Research Network  
This Article proposes that lenders operating in noncompetitive subprime mortgage markets address how their practices interact with lending disparities even apart from their complicity in creating conditions  ...  However, evidence suggests that subprime mortgage segmentation increases, rather than reduces, exclusionary practices in lending.  ...  the relevant trade-offs among factors, and assigns statistically derived weights used in the model.  ... 
doi:10.2139/ssrn.1710063 fatcat:efig4vhd4jdklolwwr7l5g5yfe

Using Minsky's Cushions of Safety to Analyze the Crisis in the U. S. Subprime Mortgage Market

Jan Kregel
2008 International Journal of Political Economy  
When margins have been sufficiently reduced, even the smallest departure of realizations from expectations creates conditions in which firms have to change plans in order to meet fixed cash-flow commitments  ...  As a result, the basic decision to lend is based on the J. P.  ...  relation to changes in financial conditions.  ... 
doi:10.2753/ijp0891-1916370101 fatcat:ejz2ug4c55hdbbckmvrd6dxwom

Predicting Consumer Default: A Deep Learning Approach [article]

Stefania Albanesi, Domonkos F. Vamossy
2019 arXiv   pre-print
Our model is interpretable and is able to provide a score to a larger class of borrowers relative to standard credit scoring models while accurately tracking variations in systemic risk.  ...  We develop a model to predict consumer default based on deep learning. We show that the model consistently outperforms standard credit scoring models, even though it uses the same data.  ...  liable business loans Chapter 7 bankruptcies Open second mortgage trades Charge-off amount on unsatisfied charge-off trades Petitioned bankruptcies Charge-off trades Public record bankruptcies Collections  ... 
arXiv:1908.11498v2 fatcat:3mni4jtq5zczngmwoslae3kw5i

A Responsible Machine Learning Workflow with Focus on Interpretable Models, Post-hoc Explanation, and Discrimination Testing

Navdeep Gill, Patrick Hall, Kim Montgomery, Nicholas Schmidt
2020 Information  
By combining interpretable models, post-hoc explanations, and discrimination testing with accessible software tools, this text aims to provide a template workflow for machine learning applications that  ...  constrained models, monotonic gradient boosting machines and explainable neural networks, a deep learning architecture well-suited for structured data, are assessed on simulated data and publicly available mortgage  ...  Additional Simulated Data Results As seen in Section 3.1.1, little or no trade-off is required in terms of model to fit to use the constrained models.  ... 
doi:10.3390/info11030137 fatcat:p6fx7lykrfaqpagtrvrqhzeora

Implications of Institutional Dispositions of Neoliberalism

Slobodan Lakic, Mimo Draskovic
2015 Montenegrin Journal of Economics  
In this document, we test the hypothesis in the case of dominating the instruments of the "market" institutions in relation to the regulatory instruments and inefficiently modeled financial markets over  ...  manipulating the selective scope of derivative and high frequency trading.  ...  Trade occurs mainly in the OTC markets, which moves away from transparency in trade;  Regulation bypassing.  ... 
doi:10.14254/1800-5845.2015/11-2/7 fatcat:hywsr7aznngtvakmsvkqxsk72i

Consumer Credit Risk Models Via Machine-Learning Algorithms

Amir E. Khandani, Adlar J. Kim, Andrew W. Lo
2010 Social Science Research Network  
applications in forecasting systemic risk.  ...  Using conservative assumptions for the costs and benefits of cutting credit lines based on machine-learning forecasts, we estimate the cost savings to range from 6% to 25% of total losses.  ...  (in which the trade-off between true and false positive rates is one-to-one; see Section 5.1).  ... 
doi:10.2139/ssrn.1568864 fatcat:ao5ispn5p5a5vjvt4atnzhjjv4
« Previous Showing results 1 — 15 out of 923 results