Stefano Filomeni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Stefano Filomeni has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Michele Modina
University of Molise
5 shared publications - Elena Tabacco
Voghera (Pavia), Italy
3 shared publications - Udichibarna Bose
University of Essex
3 shared publications Alberto Zazzaro
Department of Economic and Social Sciences, Money and Finance Research Group (MoFiR), Polytechnic University of Marche, Ancona, Italy
2 shared publicationsAlessandra Tanda
University of Pavia, Department of Economics and Management, Pavia, Italy
2 shared publications- Alessandra Tanda
Department of Economics and Management University of Pavia Pavia Italy
2 shared publications
Latest Publications
- Open Access
- 11 June 2025
- Published by Elsevier in Journal of Corporate Finance
- Vol. 94
Machine Learning for the Unlisted: Enhancing MSME Default Prediction with Public Market Signals
- 11 June 2025
- Published by Elsevier in Journal of Corporate Finance
- Vol. 94
Open AccessMachine Learning for the Unlisted: Enhancing MSME Default Prediction with Public Market Signals
- 15 January 2025
- Published by Taylor & Francis in European Accounting Review
- Vol. 34 (5) , 2033-2054
Can Soft Information Survive Organizational Distance? Evidence from SMB Lending
- 15 January 2025
- Published by Taylor & Francis in European Accounting Review
- Vol. 34 (5) , 2033-2054
Can Soft Information Survive Organizational Distance? Evidence from SMB Lending
- Open Access
- 1 January 2025
- Published by Elsevier in SSRN Electronic Journal
Can soft information survive organizational distance? Evidence from SMB lending
This paper examines whether and how soft information in corporate loan applications influences the lending decision process, and whether organizational frictions moderate this influence. In this context, soft information refers to the text data collected, analyzed, and transmitted by loan officers to the bank's headquarters. Using a proprietary dataset from a large European bank, the study finds that soft information impacts both the outcomes and the speed of lending decisions. However, this effect is moderated by the organizational distance between the loan officer and the bank's headquarters. Additionally, we provide evidence that soft information embedded in comments serves as a strong predictor of company defaults, supporting its use in lending to small and medium-sized businesses (SMBs), particularly when branches are distant from the bank's headquarters. Our findings remain robust across additional analyses and tests, consistent with the presence of communication frictions within banking organizations that hinder the effective "hardening" of soft information as organizational distance increases.
- 1 January 2025
- Published by Elsevier in SSRN Electronic Journal
Open AccessCan soft information survive organizational distance? Evidence from SMB lending
This paper examines whether and how soft information in corporate loan applications influences the lending decision process, and whether organizational frictions moderate this influence. In this context, soft information refers to the text data collected, analyzed, and transmitted by loan officers to the bank's headquarters. Using a proprietary dataset from a large European bank, the study finds that soft information impacts both the outcomes and the speed of lending decisions. However, this effect is moderated by the organizational distance between the loan officer and the bank's headquarters. Additionally, we provide evidence that soft information embedded in comments serves as a strong predictor of company defaults, supporting its use in lending to small and medium-sized businesses (SMBs), particularly when branches are distant from the bank's headquarters. Our findings remain robust across additional analyses and tests, consistent with the presence of communication frictions within banking organizations that hinder the effective "hardening" of soft information as organizational distance increases.
- Open Access
- 15 October 2024
- Published by Springer Nature in Review of Quantitative Finance and Accounting
- Vol. 64 (4) , 1783-1808
Did Biden-Harris’s reforms on the Paycheck Protection Program reduce racial disparities in lending?
Introduced under the Trump-Pence Administration, the Paycheck Protection Program (PPP) provided short-term relief loans to small American businesses during the peak of the Coronavirus pandemic. The initial design of the PPP faced significant criticism from researchers due to racial disparities, among other issues, in its lending process. Minority groups received smaller PPP loan amounts during the original two tranches released in 2020. To increase equitable access for all, in February 2021 the Biden-Harris Administration enforced swift changes to the initial PPP aimed at favouring access to PPP loans for minority-owned small businesses that had been disadvantaged by the program’s original design under the Trump-Pence Administration. By exploiting a granular dataset of 1,759,270 PPP loans granted between Q2 2020 and Q2 2021 and by implementing a difference-in-differences approach (DID), this paper provides novel evidence on the effectiveness of the Biden reforms in reducing racial disparities within the Paycheck Protection Program. Indeed, we observe a significant increase in the volume of PPP loans granted to minority-owned businesses in the period following the Biden-Harris Administration’s reforms. Furthermore, among different minority groups, the reforms appear most effective for Native American minority groups (including American Indians, Alaska Natives, Native Hawaiians and/or Other Pacific Islanders), followed by Black Americans and Asian business owners. Our findings offer novel contributions to the existing literature on institutional discrimination, particularly regarding the initial PPP design. Our findings are especially valuable for policy makers as they underscore the importance of radical changes in addressing racial disparities. Our paper also offers evidence of how a public credit guarantee program should be designed to empower and promote economic inclusion for all, regardless of ethnicity, aligning with the UN’s Sustainable Development Goals.
- 15 October 2024
- Published by Springer Nature in Review of Quantitative Finance and Accounting
- Vol. 64 (4) , 1783-1808
Open AccessDid Biden-Harris’s reforms on the Paycheck Protection Program reduce racial disparities in lending?
Introduced under the Trump-Pence Administration, the Paycheck Protection Program (PPP) provided short-term relief loans to small American businesses during the peak of the Coronavirus pandemic. The initial design of the PPP faced significant criticism from researchers due to racial disparities, among other issues, in its lending process. Minority groups received smaller PPP loan amounts during the original two tranches released in 2020. To increase equitable access for all, in February 2021 the Biden-Harris Administration enforced swift changes to the initial PPP aimed at favouring access to PPP loans for minority-owned small businesses that had been disadvantaged by the program’s original design under the Trump-Pence Administration. By exploiting a granular dataset of 1,759,270 PPP loans granted between Q2 2020 and Q2 2021 and by implementing a difference-in-differences approach (DID), this paper provides novel evidence on the effectiveness of the Biden reforms in reducing racial disparities within the Paycheck Protection Program. Indeed, we observe a significant increase in the volume of PPP loans granted to minority-owned businesses in the period following the Biden-Harris Administration’s reforms. Furthermore, among different minority groups, the reforms appear most effective for Native American minority groups (including American Indians, Alaska Natives, Native Hawaiians and/or Other Pacific Islanders), followed by Black Americans and Asian business owners. Our findings offer novel contributions to the existing literature on institutional discrimination, particularly regarding the initial PPP design. Our findings are especially valuable for policy makers as they underscore the importance of radical changes in addressing racial disparities. Our paper also offers evidence of how a public credit guarantee program should be designed to empower and promote economic inclusion for all, regardless of ethnicity, aligning with the UN’s Sustainable Development Goals.
- Open Access
- 24 September 2024
- Published by Springer Nature in Journal of Business Ethics
- Vol. 198 (2) , 437-466
Does Soft Information Mitigate Gender Bias in Corporate Lending?
Gender bias in leadership and decision-making is a well-documented and pervasive topic that continues to garner significant attention in academic research and business literature. In this paper, by exploiting a unique proprietary dataset of 550 mid-corporate loan applications managed by a major European bank, we explore how the use of soft information influences lending decisions of female loan officers as compared to their male counterparts. We find that use of soft information reduces information asymmetry which helps female officers in making diligent lending decisions resulting in increased granted credit with a lower default probability. We also investigate gender affinity within the banking organisation and find that female loan approvers are more likely to be supportive of their subordinate female loan officers by approving more credit to the loan applications handled by female loan officers. Finally, we examine the possible mechanisms that can explain these results, and find that female loan officers are able to better collect and use soft information as they cultivate and maintain deeper firm-bank relationships with their clients due to higher threat of losing or being penalized in their jobs for any possible errors. We also rule out any other possible explanations such as differences in workload, work experience, loan officers’ optimism, managerial ability, and screening capabilities between female and male loan officers. Our findings carry important policy implications, reflected in the optimal allocation of capital in the economy and the reduction of gender-related exclusion, which is vital in creating an equitable society and fostering a more ethical and inclusive workplace.
- 24 September 2024
- Published by Springer Nature in Journal of Business Ethics
- Vol. 198 (2) , 437-466
Open AccessDoes Soft Information Mitigate Gender Bias in Corporate Lending?
Gender bias in leadership and decision-making is a well-documented and pervasive topic that continues to garner significant attention in academic research and business literature. In this paper, by exploiting a unique proprietary dataset of 550 mid-corporate loan applications managed by a major European bank, we explore how the use of soft information influences lending decisions of female loan officers as compared to their male counterparts. We find that use of soft information reduces information asymmetry which helps female officers in making diligent lending decisions resulting in increased granted credit with a lower default probability. We also investigate gender affinity within the banking organisation and find that female loan approvers are more likely to be supportive of their subordinate female loan officers by approving more credit to the loan applications handled by female loan officers. Finally, we examine the possible mechanisms that can explain these results, and find that female loan officers are able to better collect and use soft information as they cultivate and maintain deeper firm-bank relationships with their clients due to higher threat of losing or being penalized in their jobs for any possible errors. We also rule out any other possible explanations such as differences in workload, work experience, loan officers’ optimism, managerial ability, and screening capabilities between female and male loan officers. Our findings carry important policy implications, reflected in the optimal allocation of capital in the economy and the reduction of gender-related exclusion, which is vital in creating an equitable society and fostering a more ethical and inclusive workplace.
- Open Access
- 6 June 2024
- Published by Springer Nature in Review of Quantitative Finance and Accounting
- Vol. 63 (3) , 925-954
Can we trust machine learning to predict the credit risk of small businesses?
With the emergence of Fintech lending, small firms can benefit from new channels of financing. In this setting, the creditworthiness and the decision to extend credit are often based on standardized and advanced machine-learning techniques that employ limited information. This paper investigates the ability of machine learning to correctly predict credit risk ratings for small firms. By employing a unique proprietary dataset on invoice lending activities, this paper shows that machine learning techniques overperform traditional techniques, such as probit, when the set of information available to lenders is limited. This paper contributes to the understanding of the reliability of advanced credit scoring techniques in the lending process to small businesses, making it a special interesting case for the Fintech environment.
- 6 June 2024
- Published by Springer Nature in Review of Quantitative Finance and Accounting
- Vol. 63 (3) , 925-954
Open AccessCan we trust machine learning to predict the credit risk of small businesses?
With the emergence of Fintech lending, small firms can benefit from new channels of financing. In this setting, the creditworthiness and the decision to extend credit are often based on standardized and advanced machine-learning techniques that employ limited information. This paper investigates the ability of machine learning to correctly predict credit risk ratings for small firms. By employing a unique proprietary dataset on invoice lending activities, this paper shows that machine learning techniques overperform traditional techniques, such as probit, when the set of information available to lenders is limited. This paper contributes to the understanding of the reliability of advanced credit scoring techniques in the lending process to small businesses, making it a special interesting case for the Fintech environment.
- Open Access
- 7 May 2024
- Published by Springer Nature in Review of Quantitative Finance and Accounting
- Vol. 63 (2) , 433-468
Securitization and risk appetite: empirical evidence from US banks
I investigate the impact of securitization on the risk-taking by bank holding companies (BHCs). For 2001 to 2017, I find a negative relationship between securitization and the risk appetite of BHCs. I find a negative relationship between securitization and the risk appetite of BHCs that is consistent with the recourse hypothesis of securitization. I also discover that the equilibrium in this relationship changes from the pre-crisis to the crisis period (crisis effect). This crisis effect hampers BHCs’ ability to engage in securitization that leads them to accumulate more risky assets on their books due to the deteriorated quality of their loan portfolios. This equilibrium then reverses after the crisis (post-crisis effect) due to policy makers’ response to the excessive risk-taking that manifested during the crisis. Moreover, I find that the securitization of residential mortgages not only boosts the recourse hypothesis but also triggers the crisis effect. My findings provide novel empirical insights into the different nexuses between the securitization and risk appetite of BHCs around the financial crisis.
- 7 May 2024
- Published by Springer Nature in Review of Quantitative Finance and Accounting
- Vol. 63 (2) , 433-468
Open AccessSecuritization and risk appetite: empirical evidence from US banks
I investigate the impact of securitization on the risk-taking by bank holding companies (BHCs). For 2001 to 2017, I find a negative relationship between securitization and the risk appetite of BHCs. I find a negative relationship between securitization and the risk appetite of BHCs that is consistent with the recourse hypothesis of securitization. I also discover that the equilibrium in this relationship changes from the pre-crisis to the crisis period (crisis effect). This crisis effect hampers BHCs’ ability to engage in securitization that leads them to accumulate more risky assets on their books due to the deteriorated quality of their loan portfolios. This equilibrium then reverses after the crisis (post-crisis effect) due to policy makers’ response to the excessive risk-taking that manifested during the crisis. Moreover, I find that the securitization of residential mortgages not only boosts the recourse hypothesis but also triggers the crisis effect. My findings provide novel empirical insights into the different nexuses between the securitization and risk appetite of BHCs around the financial crisis.
- Open Access
- 1 December 2023
- Published by Springer Nature in Review of Quantitative Finance and Accounting
- Vol. 62 (4) , 1329-1353
The impact of the Paycheck Protection Program on the risk-taking behaviour of US banks
The economic impact of the COVID-19 pandemic placed many small businesses across the US in financial distress. In response to this, in March 2020 the US government introduced, as part of the CARES Act, the Paycheck Protection Program (PPP) intended to provide relief to small businesses and to preserve jobs during the pandemic. The latter resulted in three waves of funding distributed to small businesses through SBA approved lenders, mainly represented by US banks. By using a panel dataset of 4610 banks over the period Q1 2019–Q4 2020 and by employing a difference-in-differences approach (DiD), I investigate whether participation in the Paycheck Protection Program affected community banks’ credit risk-taking behaviour in the post-PPP period, compared to their non-community banking counterparts in the US. I find that the Paycheck Protection Program led community banks to decrease their risk appetite outside of the program relative to non-community banks, consistent with their greater exposure to the commercial real estate sector, heavily hit by the pandemic. My results are robust to a battery of robustness tests and identification strategies. In this research article, I offer novel evidence on the indirect impact of the Paycheck Protection Program as a government-funded stimulus program administered through banks by investigating the indirect effect of the Paycheck Protection Program on the risk-taking of US community banks that dominate lending of PPP loans as a result of their competitive advantage in soft information-intensive small business lending. Such evidence is informative to policymakers as they weigh the merits of various program options to combat the economic damage imposed by the COVID-19 pandemic and as they consider the design of economic stimulus programs in response to future economic crises.
- 1 December 2023
- Published by Springer Nature in Review of Quantitative Finance and Accounting
- Vol. 62 (4) , 1329-1353
Open AccessThe impact of the Paycheck Protection Program on the risk-taking behaviour of US banks
The economic impact of the COVID-19 pandemic placed many small businesses across the US in financial distress. In response to this, in March 2020 the US government introduced, as part of the CARES Act, the Paycheck Protection Program (PPP) intended to provide relief to small businesses and to preserve jobs during the pandemic. The latter resulted in three waves of funding distributed to small businesses through SBA approved lenders, mainly represented by US banks. By using a panel dataset of 4610 banks over the period Q1 2019–Q4 2020 and by employing a difference-in-differences approach (DiD), I investigate whether participation in the Paycheck Protection Program affected community banks’ credit risk-taking behaviour in the post-PPP period, compared to their non-community banking counterparts in the US. I find that the Paycheck Protection Program led community banks to decrease their risk appetite outside of the program relative to non-community banks, consistent with their greater exposure to the commercial real estate sector, heavily hit by the pandemic. My results are robust to a battery of robustness tests and identification strategies. In this research article, I offer novel evidence on the indirect impact of the Paycheck Protection Program as a government-funded stimulus program administered through banks by investigating the indirect effect of the Paycheck Protection Program on the risk-taking of US community banks that dominate lending of PPP loans as a result of their competitive advantage in soft information-intensive small business lending. Such evidence is informative to policymakers as they weigh the merits of various program options to combat the economic damage imposed by the COVID-19 pandemic and as they consider the design of economic stimulus programs in response to future economic crises.
- Open Access
- 30 October 2023
- Published by Elsevier in Socio-Economic Planning Sciences
- Vol. 90
Machine learning and credit risk: Empirical evidence from small- and mid-sized businesses
- 30 October 2023
- Published by Elsevier in Socio-Economic Planning Sciences
- Vol. 90
Open AccessMachine learning and credit risk: Empirical evidence from small- and mid-sized businesses
- Open Access
- 15 June 2023
- Published by Wiley in International Journal of Finance & Economics
- Vol. 29 (3) , 3567-3592
Can market information outperform hard and soft information in predicting corporate defaults?
Recent evidence has shown that hybrid models for credit ratings are important when assessing the risk of firms. Within this stream of literature, we aim to provide novel evidence on how hard (quantitative), soft (qualitative), and market information predict corporate defaults for unlisted firms by implementing the Cox proportional hazard model. We address this research question by exploiting a unique proprietary dataset comprising of detailed information on internal credit ratings of European unlisted mid‐sized firms and compute their Merton's distance‐to‐default (DD) measure of credit risk with market data collected on comparable publicly listed companies. Our results show that the bank's use of hard, soft, and market information when assessing the credit ratings of borrowers has a significant influence on the prediction of their defaults. Further, we investigate the significant influence of soft information in predicting corporate defaults by drawing on two separate processes through which loan officers can inject soft information in credit scoring, that is, ‘codified’ and ‘uncodified’ discretion. Finally, when we distinguish between the loan officer's discretion to upgrade or downgrade an applicant's credit score, we find that it is the upgrade that is likely to predict a lower probability of a firm defaulting. This study contributes to the policy debate on safeguarding the banking sector's continuity by positing that integrating market information into banks' hybrid methods of credit rating helps to improve the accuracy in predicting unlisted firms' credit risk that is useful to policy makers for the design of future forward‐looking financial risk management frameworks.
- 15 June 2023
- Published by Wiley in International Journal of Finance & Economics
- Vol. 29 (3) , 3567-3592
Open AccessCan market information outperform hard and soft information in predicting corporate defaults?
Recent evidence has shown that hybrid models for credit ratings are important when assessing the risk of firms. Within this stream of literature, we aim to provide novel evidence on how hard (quantitative), soft (qualitative), and market information predict corporate defaults for unlisted firms by implementing the Cox proportional hazard model. We address this research question by exploiting a unique proprietary dataset comprising of detailed information on internal credit ratings of European unlisted mid‐sized firms and compute their Merton's distance‐to‐default (DD) measure of credit risk with market data collected on comparable publicly listed companies. Our results show that the bank's use of hard, soft, and market information when assessing the credit ratings of borrowers has a significant influence on the prediction of their defaults. Further, we investigate the significant influence of soft information in predicting corporate defaults by drawing on two separate processes through which loan officers can inject soft information in credit scoring, that is, ‘codified’ and ‘uncodified’ discretion. Finally, when we distinguish between the loan officer's discretion to upgrade or downgrade an applicant's credit score, we find that it is the upgrade that is likely to predict a lower probability of a firm defaulting. This study contributes to the policy debate on safeguarding the banking sector's continuity by positing that integrating market information into banks' hybrid methods of credit rating helps to improve the accuracy in predicting unlisted firms' credit risk that is useful to policy makers for the design of future forward‐looking financial risk management frameworks.