Bad Taste: Gender Discrimination in the Consumer Credit Market

Montoya, Ana Maria; Parrado, Eric; Solis, Alex; Undurraga, Raimundo

doi:10.18235/0001921

Cited by 16 publications

(8 citation statements)

References 63 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One such example is found in Montoya et al. (2020) where loan applications submitted by women are almost 20% less likely to be approved. In addition, because this type of behavior is both socially and economically unacceptable, it is measured if female loan officers are having overconfidence bias.…”

Section: Related Workmentioning

confidence: 98%

“…This effect, called overconfidence bias, says that male grant-officers tend to overestimate the probability of returning the credit to male individuals rather than female individuals. One such example is found in Montoya et al (2020) where loan applications submitted by women are almost 20% less likely to be approved. In addition, because this type of behavior is both socially and economically unacceptable, it is measured if female loan officers are having overconfidence bias.…”

Section: Gender Bias In Bankingmentioning

confidence: 99%

See 1 more Smart Citation

A fair classifier chain for multi‐label bank marketing strategy classification

Radovanović

Petrović

Delibašić

et al. 2021

Int Trans Operational Res

View full text Add to dashboard Cite

Recently, the usage of machine learning algorithms is subject to discussion from a legal and ethical point of view. Unwanted discrimination regarding gender or race of a prediction model can lead to legal consequences. Therefore, during predictive model learning, one needs to be aware of possible bias and adjust the model to be fair. However, in bank marketing applications, one customer can receive multiple offers instead of just one. Because of their correlation between, a multi-label classification approach is the most suitable one. This paper proposes a fair classifier chain machine learning model for multi-label classification. Our algorithm solves the multi-label classification problem in an efficient manner, and it is suitable for real-life application employment. The proposed approach allows for controlling fairness constraints during the process of machine learning. It is based on the logistic regression model, thus enabling high efficiency and understandability. We apply our model to a real-life model from bank marketing campaign response prediction. The obtained results are promising. More specifically, our model achieves high fairness measures having an increase from 7% to 17%. However, fairness has a price of a decrease in predictive performance, up to 9% of AUC. To the best of our knowledge, this is the first algorithm that introduce fairness constraints in multi-label classification problems.

show abstract

Section: Related Workmentioning

confidence: 98%

Section: Gender Bias In Bankingmentioning

confidence: 99%

A fair classifier chain for multi‐label bank marketing strategy classification

Radovanović

Petrović

Delibašić

et al. 2021

Int Trans Operational Res

View full text Add to dashboard Cite

show abstract

“…See, for example, Carter et al (2007), Muravyev, Talavera, and Schafer (2009), Barasinska and Schafer (2010), Bellucci, Borisov, and Zazzaro (2010), Agier and Szafarz (2013), Alesina, Lotti, and Mistrulli (2013), Stefani and Vacca (2013), Mascia and Rossi (2017), and Beck, Behr, and Madestam (2018). A recent study on the Chilean loan market, for example, aimed to identify how loan officers respond to identical loan requests from men and women (Montoya et al, 2020). If there were differences in loan approvals, the authors wanted to determine how much of that was due to an objective evaluation of the candidate's ability to repay the loan and how much was simply outand-out gender prejudice.…”

Section: Gender Discrimination In Lendingmentioning

confidence: 99%

Dealing with Debt: Less Risk for More Growth in Latin America and the Caribbean

Powell,

Valencia

2023

View full text Add to dashboard Cite

Debt has risen around the world, and Latin America and the Caribbean is no exception. Total debt has grown to US$5.8 trillion, or 117 percent of GDP, for the region and as much as 140 percent of GDP for its five largest economies. Public debt soared to over 70 percent of GDP during the pandemic, and corporates issued substantial amounts to survive the crisis. While the spending that led to this debt helped the region weather the pandemic, it is now weighing down the economy. This book examines the rise in debt in Latin America and the Caribbean and offers recommendations to policymakers to ensure debt is used wisely, avoid the harmful impacts, manage high debt levels well, and bring down debt where it is too high. It is hoped that the analyses and policy suggestions in this volume contribute to successfully confronting the challenges, lowering risk, boosting growth, and improving living standards across the region and beyond.

show abstract

“…masks and hand sanitizer) (Ratten, 2020b). In this scenario, in the case of female entrepreneurs, recent empirical evidence of developing countries suggests that they have been mainly affected in terms of sales, household income, lifestyle and mental health, which, in turn, has led many of them to close their businesses (Mustafa et al , 2021). According to the World Bank (2020), due to the COVID-19 crisis, confinement measures have disproportionately affected female entrepreneurs.…”

Section: Female Entrepreneurs’ Performance In Crisis Contextmentioning

confidence: 99%

“…In this sense, the authors analyse, in addition to banks, other possible funding sources at hand such as personal savings, friends’ loans, government’s loans and other forms of financing as venture capital and angel investors. For instance, due to the COVID-19 crisis, some women entrepreneurs in developing countries resorted to their own savings in the absence of income (Mustafa et al , 2021). Kwong et al (2019) highlight the importance of financial bricolage in the acquisition of external resources when resources are constrained, such as in the case of displaced entrepreneurs (those who have been forced to leave their countries by persecution, war or violence).…”

Section: A Theory Of Learning To Address Entrepreneurship In Crisis C...mentioning

confidence: 99%

Entrepreneurial bricolage: crowdfunding for female entrepreneurs during COVID-19 pandemic

Alva

Vivas

Urcia

2021

JEEE

View full text Add to dashboard Cite

Purpose The crisis generated by the COVID-19 pandemic has had unprecedented effects around the world and particularly on vulnerable populations, such as female entrepreneurs in developing countries. They are facing a new normal, characterized by high uncertainty and resource constraints. This paper aims to use the experiential learning theory applied to entrepreneurship to propose the entrepreneurial bricolage approach to study how female entrepreneurs can overcome this type of crisis. Design/methodology/approach Within the research designs of conceptual papers, the study is situated within the model approach because the authors propose novel relationships between constructs to answer the research questions through the development of theoretical propositions. Findings The analysis suggests that the entrepreneurial bricolage process represents a type of strategy that allows these women to adapt to this new normal. Based on this approach, the authors suggest that crowdfunding represents a financial resource at hand for both pre-existing female entrepreneurs and new female entrepreneurs. Practical implications The theoretical implications suggest an alternative conceptual framework of the entrepreneurial bricolage process to analyse the female entrepreneurial activity in developing countries and during crisis’ contexts. The managerial implications suggest that crowdfunding is a financial resource at hand for female entrepreneurs that allow them to perform well, innovate or implement growth strategies and have more chances of surviving and growing during the crisis. Finally, the policy implications are oriented to the promotion of this kind of financial alternative and the generation of trust for users, along with the strengthening of a regulatory framework to attract more investors and entrepreneurs. Originality/value This study provides useful information on how the crisis generated by the COVID-19 pandemic has been affecting female entrepreneurs in developing countries. It also expands on the literature on crowdfunding in terms of its advantages as a non-traditional funding source for women.

show abstract

Bad Taste: Gender Discrimination in the Consumer Credit Market

Cited by 16 publications

References 63 publications

A fair classifier chain for multi‐label bank marketing strategy classification

A fair classifier chain for multi‐label bank marketing strategy classification

Dealing with Debt: Less Risk for More Growth in Latin America and the Caribbean

Entrepreneurial bricolage: crowdfunding for female entrepreneurs during COVID-19 pandemic

Contact Info

Product

Resources

About