Machine learning with kernels for portfolio valuation and risk management

Machine learning has successful applications in credit risk management, portfolio management, automatic trading, and fraud detection, to name a few, in the domain of finance technology. Reformulating and solving these topics adequately and accurately is problem specific and challenging along with the availability of complex and voluminous data. In credit risk management, one major problem is to predict the default of credit card holders using real dataset. We review five machine learning methods: the [Formula: see text]-nearest neighbors decision trees, boosting, support vector machine, and neural networks, and apply them to the above problem. In addition, we give explicit Python scripts to conduct analysis using a dataset of 29,999 instances with 23 features collected from a major bank in Taiwan, downloadable in the UC Irvine Machine Learning Repository. We show that the decision tree performs best among others in terms of validation curves.

Download Full-text

Tie me to the mast: artificial intelligence & reputation risk management

Journal of Business Strategy ◽

10.1108/jbs-11-2017-0160 ◽

2018 ◽

Vol 39 (1) ◽

pp. 61-64 ◽

Cited By ~ 8

Author(s):

Peter Buell Hirsch

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Risk Management ◽

Thought Experiment ◽

Early Stage ◽

Stress Test ◽

Risky Behaviors ◽

Content Type ◽

Early Signs ◽

Reputation Risk

Purpose Artificial intelligence and machine learning have spread rapidly across every aspect of business and social activity. The purpose of this paper is to examine how this rapidly growing field of analytics might be put to use in the area of reputation risk management. Design/methodology/approach The approach taken was to examine in detail the primary and emerging applications of artificial intelligence to determine how they could be applied to preventing and mitigating reputation risk by using machine learning to identify early signs of behaviors that could lead to reputation damage. Findings This review confirmed that there were at least two areas in which artificial intelligence could be applied to reputation risk management – the use of machine learning to analyze employee emails in real time to detect early signs of aberrant behavior and the use of algorithmic game theory to stress test business decisions to determine whether they contained perverse incentives leading to potential fraud. Research limitations/implications Because of the fact that this viewpoint is by its nature a thought experiment, the authors have not yet tested the practicality or feasibility of the uses of artificial intelligence it describes. Practical implications Should the concepts described be viable in real-world application, they would create extraordinarily powerful tools for companies to identify risky behaviors in development long before they had run far enough to create major reputation risk. Social implications By identifying risky behaviors at an early stage and preventing them from turning into reputation risks, the methods described could help restore and maintain trust in the relationship between companies and their stakeholders. Originality/value To the best of the author’s knowledge, artificial intelligence has never been described as a potential tool in reputation risk management.

Download Full-text

New Entropy Based Distance for Training Set Selection in Debt Portfolio Valuation

International Journal of Information Technology and Web Engineering ◽

10.4018/jitwe.2012040105 ◽

2012 ◽

Vol 7 (2) ◽

pp. 60-69

Author(s):

Tomasz Kajdanowicz ◽

Slawomir Plamowski ◽

Przemyslaw Kazienko

Keyword(s):

Machine Learning ◽

Distance Measure ◽

Prediction Performance ◽

Training Set ◽

Learning Tasks ◽

Real Domain ◽

Valuation Process ◽

Proper Training ◽

Training Set Selection ◽

Portfolio Valuation

Choosing a proper training set for machine learning tasks is of great importance in complex domain problems. In the paper a new distance measure for training set selection is presented and thoroughly discussed. The distance between two datasets is computed using variance of entropy in groups obtained after clustering. The approach is validated using real domain datasets from debt portfolio valuation process. Eventually, prediction performance is examined.

Download Full-text

Building an Intelligent Hydroinformatics Integration Platform for Regional Flood Inundation Warning Systems

Water ◽

10.3390/w11010009 ◽

2018 ◽

Vol 11 (1) ◽

pp. 9 ◽

Cited By ~ 18

Author(s):

Li-Chiu Chang ◽

Fi-John Chang ◽

Shun-Nien Yang ◽

I-Feng Kao ◽

Ying-Yu Ku ◽

...

Keyword(s):

Machine Learning ◽

Risk Management ◽

Flood Risk ◽

Modular Design ◽

Data Access ◽

Flood Risk Management ◽

Flood Inundation ◽

Warning Systems ◽

Integration Platform ◽

Flood Disasters

Flood disasters have had a great impact on city development. Early flood warning systems (EFWS) are promising countermeasures against flood hazards and losses. Machine learning (ML) is the kernel for building a satisfactory EFWS. This paper first summarizes the ML methods proposed in this special issue for flood forecasts and their significant advantages. Then, it develops an intelligent hydroinformatics integration platform (IHIP) to derive a user-friendly web interface system through the state-of-the-art machine learning, visualization and system developing techniques for improving online forecast capability and flood risk management. The holistic framework of the IHIP includes five layers (data access, data integration, servicer, functional subsystem, and end-user application) and one database for effectively dealing with flood disasters. The IHIP provides real-time flood-related data, such as rainfall and multi-step-ahead regional flood inundation maps. The interface of Google Maps fused into the IHIP significantly removes the obstacles for users to access this system, helps communities in making better-informed decisions about the occurrence of floods, and alerts communities in advance. The IHIP has been implemented in the Tainan City of Taiwan as the study case. The modular design and adaptive structure of the IHIP could be applied with similar efforts to other cities of interest for assisting the authorities in flood risk management.

Download Full-text

AI and Machine Learning for Risk Management

SSRN Electronic Journal ◽

10.2139/ssrn.3201337 ◽

2018 ◽

Cited By ~ 5

Author(s):

Saqib Aziz ◽

Michael M. Dowling

Keyword(s):

Machine Learning ◽

Risk Management

Download Full-text