The objective of this paper is twofold. First, it develops a prediction system to help the credit card issuer model the credit card delinquency risk. Second, it seeks to explore the potential of deep learning (also called a deep neural network), an emerging artificial intelligence technology, in the credit risk domain. With real-life credit card data linked to 711,397 credit card holders from a large bank in Brazil, this study develops a deep neural network to evaluate the risk of credit card delinquency based on the client's personal characteristics and the spending behaviours. Compared with machine-learning algorithms of logistic regression, naive Bayes, traditional artificial neural networks, and decision trees, deep neural networks have a better overall predictive performance with the highest F scores and area under the receiver operating characteristic curve. The successful application of deep learning implies that artificial intelligence has great potential to support and automate credit risk assessment for financial institutions and credit bureaus. 相似文献
Bureaucracies are usually regarded as inefficient, wasteful mechanisms. Contrary to this deeply rooted perception of bureaucracy, this paper documents the case of the correctional authorities in Washington State, a bureaucracy that acted with a considerable degree of innovation and professionalism. Their task was to administer a risk assessment instrument that measured the level of risk posed by offenders by way of a numerical score. They used that score to identify the level of supervision offenders were to receive once released into the community. In analyzing the data, I discovered an unusual application of the instrument that resulted in many offenders being bumped to a higher supervision level. Using a regression discontinuity design, I uncover the mechanics of the bumping-up process and I generate an instrument that is cleansed of the manipulation. I find that the manipulated instrument predicts serious recidivism events better than the cleansed instrument, especially when these events involve high-risk offenders, thus providing evidence that the authorities had good reason to undertake the manipulation. 相似文献
Popular teamwork assessments have been strongly criticized on the grounds of poor psychometric properties and their disconnect with conceptual models of teamwork. These issues raise concerns with respect to our ability to evaluate efforts devoted to advancing teamwork in academia. We report the development of a teamwork assessment that builds on empirically supported conceptualizations of team processes. Two studies were conducted to test and to cross-validate the psychometrics of the resulting measure. In the discussion section, we address the implications of our findings for conceptual models of teamwork and provide guidelines for using the measure in business education. 相似文献
Background: Validation of overall survival (OS) extrapolations of immune-checkpoint inhibitors (ICIs) during the National Institute for Health and Care Excellence (NICE) Single Technology Assessment (STA) process is limited due to data still maturing at the time of submission. Inaccurate extrapolation may lead to inappropriate decision-making. The availability of more mature trial data facilitates a retrospective analysis of the plausibility and validity of initial extrapolations. This study compares these extrapolations to subsequently available longer-term data.
Methods: A systematic search of completed NICE appraisals of ICIs from March 2000 to December 2017 was performed. A targeted search was also undertaken to procure published OS data from the pivotal clinical trials for each identified STA made available post-submission to NICE. Initial Kaplan-Meier curves and associated extrapolations from NICE documentation were extracted to compare the accuracy of OS projections versus the most mature data.
Results: The review identified 11 STAs, of which 10 provided OS data upon submission to NICE. The extrapolations undertaken considered parametric or piecewise survival models. Additional data cut-offs provided a mean of 18 months of OS beyond the end of the original data. Initial extrapolations typically under-estimated OS from the most mature data cut-off by 0.4–2.7%, depending on the choice of assessment method and use of the manufacturer- or ERG-preferred extrapolation.
Conclusion: Long-term extrapolation of OS is required for NICE STAs based on initial immature OS data. The results of this study demonstrate that the initial OS extrapolations employed by manufacturers and ERGs generally predicted OS reasonably well when compared to more mature data (when available), although on average they appeared to underestimate OS. This review and validation shows that, while the choice of OS extrapolation is uncertain, the methods adopted are generally aligned with later-published follow-up data and appear appropriate for informing HTA decisions. 相似文献
This paper examines the environmental sustainability practices of multinational mining companies in addressing their impacts and promoting the sustainable development of local communities in Ghana. Although large-scale mining companies have embraced environmental sustainability, the drivers and the mechanisms for addressing their impacts throughout the mine life cycle is not fully understood because of the limited research in this area. The focus in this study involves an examination of the drivers for environmental sustainability in a weak and non-enabling institutional context and the mechanisms for addressing impacts on biodiversity, water quality and quantity, and ambient climate. The findings show that the environmental sustainability practices of multinational mining companies are determined by regulatory compliance and corporate environmental responsibility based on perceived ethical obligation. Additionally, we find gaps in mine closure planning and rehabilitation because of the limited requirement for biodiversity restoration in the domains of flora repopulation and active fauna reintroduction. This paper provides empirical and theoretical insights for academics and practitioners in industry and policymaking. 相似文献
This paper aimed to present an original approach for solving the aircraft stand allocation (SA) problem dynamically when due to operational disturbances, the planned allocation cannot be accomplished. The proposed Multiple-criteria Dynamic Stand Allocation (MDSA) method uses fuzzy logic to support decision-making under uncertainty. The MDSA method provides effective solutions in a short time, necessary for traffic management in case of delays, emergency, and untypical cases. It considers partially conflicting points of view of different airport users (airport managers, air traffic controllers, airlines, handling agents, and passengers) and may significantly support managers on the SA problem. The approach proposed can also be used for creating an initial SA plan for a considerable number of aircraft. 相似文献