edwin baidoo - Academia.edu (original) (raw)
Papers by edwin baidoo
The Journal of finance/The journal of finance, Apr 17, 2024
Social Science Research Network, 2023
International Journal of Applied Logistics
To be successful, BDA applications must be capable of producing actionable information useful to ... more To be successful, BDA applications must be capable of producing actionable information useful to support managerial decisions throughout the organization. Some authors have proposed that BDA projects differ from IT projects by requiring extra analytical capabilities, special software, and more specialized application developers to enhance decision modelling effectiveness. This study used a two-respondent survey of decision makers using BDA applications fully operational for between 1-3 years and the corresponding CDOs in 282 organizations in various industry sectors. Using stepwise multivariate regression analysis, this convenience sample with a response rate of 32% was used to test hypotheses regarding the importance of some factors proposed in the literature as likely to improve the success of BDA applications. The results corroborate the importance of these factors by explaining a substantial percentage of the variance in decision modelling effectiveness and support several insig...
SSRN Electronic Journal, 2021
Atlantic Marketing Journal, 2021
Big Data methodologies are applied to understand subprime borrowers in the U.S. automobile space.... more Big Data methodologies are applied to understand subprime borrowers in the U.S. automobile space. The focus on the automobile market is essential as this subsegment is responsible for directly and indirectly employing over one million people and creating payrolls in excess of $100 billion annually in the U.S. It is found in this article that if a subprime borrower is a homeowner, the probability of repaying their auto loan increases by almost 4%. However, if the borrower is renting, the likelihood of repaying their auto loan increases by nearly 1.4%. Applying Big Data in making subprime auto loans can add 1000's of jobs and improve security of millions of dollars in payroll.
The purpose of this study is to ascertain the statistical and economic signicance of non-traditio... more The purpose of this study is to ascertain the statistical and economic signicance of non-traditional credit data for individuals who do not have sucient economic data, collectively known as the unbanked and underbanked. The consequences of not having sucient economic information often determines whether unbanked and underbanked individuals will receive higher price of credit or be denied entirely. In terms of regulation, there is a strong interest in credit models that will inform policies on how to gradually move sections of the unbanked and underbanked population into the general nancial network. In Chapter 2 of the dissertation, I establish the role of non-traditional credit data, known as alternative data, in modeling borrower default behavior for individuals who unbanked and underbanked individuals by taking a statistical approach. Further, using a combined traditional and alternative auto loan data, I am able to make statements about which alternative data variables contribute to borrower default behavior. Additionally, I devise a way to statistically test the goodness of t metric for some machine learning classication models to ascertain whether the alternative data truly helps in the credit building process.
Journal of Behavioral and Experimental Finance, 2021
Abstract Profit scoring represents a shift from default risk modeling. Here, lenders align their ... more Abstract Profit scoring represents a shift from default risk modeling. Here, lenders align their lending strategies to reflect their profitability objective. This paper proposes models that address the lender’s profit maximization objective. We develop varying cutoff functions that inform lending decisions while considering a lender’s attitude towards risk and loss. We derive two propositions about the properties of the variable cutoff functions for risk-averse and loss-averse lenders. Using a proprietary consumer loan data set, we show the effect of cutoff functions in lending decisions and find that both risk-averse and loss-averse lenders are profitable if they use parameter estimators that support their profitability objective.
This paper analyzes the accuracy rates for logistic regression and time series models. It also ex... more This paper analyzes the accuracy rates for logistic regression and time series models. It also examines a relatively new performance index that takes into consideration the business assumptions of credit markets. Although prior research has focused on evaluation metrics, such as AUC and Gini index, this new measure has a more intuitive interpretation for various managers and decision makers and can be applied to both Logistic and Time Series models.
The Journal of finance/The journal of finance, Apr 17, 2024
Social Science Research Network, 2023
International Journal of Applied Logistics
To be successful, BDA applications must be capable of producing actionable information useful to ... more To be successful, BDA applications must be capable of producing actionable information useful to support managerial decisions throughout the organization. Some authors have proposed that BDA projects differ from IT projects by requiring extra analytical capabilities, special software, and more specialized application developers to enhance decision modelling effectiveness. This study used a two-respondent survey of decision makers using BDA applications fully operational for between 1-3 years and the corresponding CDOs in 282 organizations in various industry sectors. Using stepwise multivariate regression analysis, this convenience sample with a response rate of 32% was used to test hypotheses regarding the importance of some factors proposed in the literature as likely to improve the success of BDA applications. The results corroborate the importance of these factors by explaining a substantial percentage of the variance in decision modelling effectiveness and support several insig...
SSRN Electronic Journal, 2021
Atlantic Marketing Journal, 2021
Big Data methodologies are applied to understand subprime borrowers in the U.S. automobile space.... more Big Data methodologies are applied to understand subprime borrowers in the U.S. automobile space. The focus on the automobile market is essential as this subsegment is responsible for directly and indirectly employing over one million people and creating payrolls in excess of $100 billion annually in the U.S. It is found in this article that if a subprime borrower is a homeowner, the probability of repaying their auto loan increases by almost 4%. However, if the borrower is renting, the likelihood of repaying their auto loan increases by nearly 1.4%. Applying Big Data in making subprime auto loans can add 1000's of jobs and improve security of millions of dollars in payroll.
The purpose of this study is to ascertain the statistical and economic signicance of non-traditio... more The purpose of this study is to ascertain the statistical and economic signicance of non-traditional credit data for individuals who do not have sucient economic data, collectively known as the unbanked and underbanked. The consequences of not having sucient economic information often determines whether unbanked and underbanked individuals will receive higher price of credit or be denied entirely. In terms of regulation, there is a strong interest in credit models that will inform policies on how to gradually move sections of the unbanked and underbanked population into the general nancial network. In Chapter 2 of the dissertation, I establish the role of non-traditional credit data, known as alternative data, in modeling borrower default behavior for individuals who unbanked and underbanked individuals by taking a statistical approach. Further, using a combined traditional and alternative auto loan data, I am able to make statements about which alternative data variables contribute to borrower default behavior. Additionally, I devise a way to statistically test the goodness of t metric for some machine learning classication models to ascertain whether the alternative data truly helps in the credit building process.
Journal of Behavioral and Experimental Finance, 2021
Abstract Profit scoring represents a shift from default risk modeling. Here, lenders align their ... more Abstract Profit scoring represents a shift from default risk modeling. Here, lenders align their lending strategies to reflect their profitability objective. This paper proposes models that address the lender’s profit maximization objective. We develop varying cutoff functions that inform lending decisions while considering a lender’s attitude towards risk and loss. We derive two propositions about the properties of the variable cutoff functions for risk-averse and loss-averse lenders. Using a proprietary consumer loan data set, we show the effect of cutoff functions in lending decisions and find that both risk-averse and loss-averse lenders are profitable if they use parameter estimators that support their profitability objective.
This paper analyzes the accuracy rates for logistic regression and time series models. It also ex... more This paper analyzes the accuracy rates for logistic regression and time series models. It also examines a relatively new performance index that takes into consideration the business assumptions of credit markets. Although prior research has focused on evaluation metrics, such as AUC and Gini index, this new measure has a more intuitive interpretation for various managers and decision makers and can be applied to both Logistic and Time Series models.