Machine learning methods for short-term probability of default: A comparison of classification, regression and ranking methods

Coenen, Lize; Verbeke, Wouter; Guns, Tias

doi:10.1080/01605682.2020.1865847

Cited by 17 publications

(5 citation statements)

References 41 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Considering the overdue days, the regression of overdue days, making the machine learning rank the events based on the risk-related ranking is what their model does. They finally show that a regression model can result in higher profits and better spread the risk [43].…”

Section: Credit Scoring and Risk Managementmentioning

confidence: 95%

Is artificial intelligence and machine learning changing the ways of banking: a systematic literature review and meta analysis

Kalyani,

Gupta

2023

Discov Artif Intell

View full text Add to dashboard Cite

This study aims to analyze the research work and present an SLR (Systematic Literature Review) on the initiatives taken by players in the banking sector, especially toward the technological innovations done in the field of AI (Artificial Intelligence) and ML (Machine Learning) that have contributed to the growth of the sector as well towards the ease of doing and building trust amongst consumers in the digitalized era of Banking. Growing security risks in cyberspace accompany the enormous and complex digital versions of virtual services. In total, 734 articles were reviewed to explore how Artificial Intelligence and Machine Learning have been used in various banking facets and how they have evolved to cater to different banking sector requirements. The findings reveal the areas where these modern-age technologies have been adopted and where the same can be used efficiently. Lastly, this study elaborates and evaluates the applications of these technologies on the parameters of scalability going further, keeping in mind the unprecedented dynamic times, and serving the very purpose of banks and how the banks are dealing with all the opportunities and challenges these new technologies bring in. This SLR also provides an overview of the research that can be taken up in future by the researchers in this domain.

show abstract

Section: Credit Scoring and Risk Managementmentioning

confidence: 95%

Is artificial intelligence and machine learning changing the ways of banking: a systematic literature review and meta analysis

Kalyani,

Gupta

2023

Discov Artif Intell

View full text Add to dashboard Cite

show abstract

“…OLS selects the parameters as a linear function of a set of explanatory variables by the principle of least squares, i.e., minimising the sum of squares of the residuals between the dependent variable (the value of the predicted variable) and the predictor variables observed in a given data set. This is one of the most basic forms of LGD regression analysis [45,46].…”

Section: Supervised MLmentioning

confidence: 99%

Assessing the Loss Given Default of Bank Loans Using the Hybrid Algorithms Multi-Stage Model

Fan,

Wu,

Zhao

2023

Systems

View full text Add to dashboard Cite

The loss given default (LGD) is an important credit risk parameter in the regulatory system for financial institutions. Due to the complex structure of the LGD distribution, we propose a new approach, called the hybrid algorithms multi-stage (HMS) model, to construct a multi-stage LGD prediction model and test it on the US Small Business Administration (SBA)’s small business credit dataset. We then compare the model’s performance under four routes by different evaluation metrics. Finally, pertinent business information and macroeconomic features datasets are added for robustness validation. The results show that HMS performs well and stably for predicting LGD, confirming the superiority of the proposed hybrid unsupervised and supervised machine learning algorithm. Financial institutions can apply the approach to make default predictions based on other credit datasets.

show abstract

“…To improve the accuracy and speed of identifying tweets based on their polarities, the authors in [14] implemented an ensemble classifier which made use of Twitter sentiment techniques. A ranking method [15] and Skip-gram meter, Word2Vec [16], were combined with a resource-based method using linguistic knowledge in their design. Text clustering techniques can be used to establish multi-level ontological linkages and identify semantic linkages between topic ideas in the framework of a knowledge graph [17].…”

Section: Related Workmentioning

confidence: 99%

Cluster-Based Knowledge Graph and Entity-Relation Representation on Tourism Economical Sentiments

et al. 2022

View full text Add to dashboard Cite

The tourism industry has experienced fast and sustainable growth over the years in the economic sector. The data available online on the ever-growing tourism sector must be given importance as it provides crucial economic insights, which can be helpful for consumers and governments. Natural language processing (NLP) techniques have traditionally been used to tackle the issues of structuring of unprocessed data, and the representation of the data in a knowledge-based system. NLP is able to capture the full richness of the text by extracting the entity and relationship from the processed data, which is gathered from various social media platforms, webpages, blogs, and other online sources, while successfully taking into consideration the semantics of the text. With the purpose of detecting connections between tourism and economy, the research aims to present a visual representation of the refined data using knowledge graphs. In this research, the data has been gathered from Twitter using keyword extraction techniques with an emphasis on tourism and economy. The research uses TextBlob to convert the tweets to numeric vector representations and further uses clustering techniques to group similar entities. A cluster-wise knowledge graph has been constructed, which comprises a large number of relationships among various factors, that visualize entities and their relationships connecting tourism and economy.

show abstract

Machine learning methods for short-term probability of default: A comparison of classification, regression and ranking methods

Cited by 17 publications

References 41 publications

Is artificial intelligence and machine learning changing the ways of banking: a systematic literature review and meta analysis

Is artificial intelligence and machine learning changing the ways of banking: a systematic literature review and meta analysis

Assessing the Loss Given Default of Bank Loans Using the Hybrid Algorithms Multi-Stage Model

Cluster-Based Knowledge Graph and Entity-Relation Representation on Tourism Economical Sentiments

Contact Info

Product

Resources

About