Large-Scale Data-Driven Financial Risk Modeling Using Big Data Technology (original) (raw)
Related papers
Big data analysis for financial risk management
2016
A very important area of financial risk management is systemic risk modelling, which concerns the estimation of the interrelationships between financial institutions, with the aim of establishing which of them are more central and, therefore, more contagious/subject to contagion.
Limits and Opportunities of Big Data For Macro-Prudential Modeling of Financial Systemic Risk
Proceedings of the International Workshop on Data Science for Macro-Modeling, 2014
We explore the use of "big data", i.e. large unstructured data sets, within financial risk analysis. We conclude it has value, but structured data remain critical. We show that forward-looking financial analysis on the systemic level needs a data structure that represents financial contracts as algorithms that produce state contingent cash flows. Currently the industry lacks such a standard, which precludes meaningful systemic forward-looking analysis. We introduce ACTUS as an emerging standard that will enable consistent analysis on all levels. This standard will also create an infrastructure for macro financial analysis 1 .
BIG DATA: A survey paper on credit risk management
Journal of emerging technologies and innovative research, 2020
Big data is a buzzword that indicates data that do not fit traditional database structure. Their potential is enormous for many fields, and risk management is within the ones that could benefit the most from new sources of unstructured data. This paper introduces the big data framework, terminology, and technology, in order to understand the upsides and challenges that they pose to financial markets. A review of standard methods and tools in risk management is then provided, in order to be able to understand the revolution brought into the environment by big data. Simulation and forecasting are the two areas that are affected the most, and therefore the ones of interest for this study. Nowadays banks operate in changing environment influenced by regulatory requirements, emerging risk types and competition on the market. At the same time banks have available large datasets arising from internal and external sources. The potential for this data usage in risk management has only recent...
IEEE, 2023
The banking industry has experienced significant transformations in terms of how effectively they function and provide services over the past few decades. The banking services infrastructure will be challenged by an expanding worldwide population. While serving a sizable segment of clients, it improves the number of consumers, online transactions, and produces enormous amounts of data. Today, banks in the US and other nations use Big Data Analytics (BDA) to handle this scenario daily. It looks for different trends in their databases in order to help their organizations make more money. Banks are changing from a straightforward approach to managing credit risk to a comprehensive risk management methodology. Banking dangers originate from numerous systems and channels. Big data technology offers an insightful and effective method for managing data, making it appropriate for use in risk management applications that call for complicated data analysis and increased data. The big data architecture of a banking credit investigation and integrated risk management system is described in this analysis. Comparisons and analyses unambiguously show that the described system performs better. Hence, this model shows that efficiency and security has improved.
Framework for big data usage in risk management process in banking institutions
2016
Nowadays banks operate in changing environment influenced by regulatory requirements, emerging risk types and competition on the market. At the same time banks have available large datasets arising from internal and external sources. The potential for this data usage in risk management has only recently been discovered and has not been the subject of extensive scientific research. There are two goals of this paper. Firstly, authors give an overview of available scientific literature and practical research related to big data usage in risk management in banks. Secondly, based on the literature review authors are presenting framework with specified detailed use of big data in specific key risk management areas. Expected contribution of this paper is in presenting framework that can be used for practical purposes in banking industry as a matrix for using big data in certain risk management area. Second expected contribution is in increasing scientific public awareness on the topic and on the potential of research in the field of big data technologies usage in risk management in banks.
2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), 2018
Banks are shifting from a simple credit risk management model to the comprehensive risk management model. Banking risks come from many channels and systems. Big data technology provides an innovative and effective solution for data management, and thus is suitable to be applied in the risk management scenarios that require high-quality data and complex data analysis. This paper firstly proposes big data architecture of hybrid processing engines and databases. This architecture uses Hadoop ecosystem with ETL and Spark processing engines, and using massive parallel processing databases (MPP), transactional databases, and HDFS. Then a banking comprehensive risk management system prototype based on the proposed big data architecture is implemented. Comparisons and evaluations clearly demonstrate that the proposed system has better performance.
QuPARA: Query-driven large-scale portfolio aggregate risk analysis on MapReduce
2013 IEEE International Conference on Big Data, 2013
Modern insurance and reinsurance companies use stochastic simulation techniques for portfolio risk analysis. Their risk portfolios may consist of thousands of reinsurance contracts covering millions of individually insured locations. To quantify risk and to help ensure capital adequacy, each portfolio must be evaluated in up to a million simulation trials, each capturing a different possible sequence of catastrophic events (e.g., earthquakes, hurricanes, etc.) over the course of a contractual year.
A Review of Selected Aspects of Big Data Usage in Banks’ Risk Management
Journal of information and organizational sciences, 2020
Contemporary banks operate in a changing environment influenced by regulatory requirements, emerging new risk types and high competition on the market. At the same time banks have on their disposal large datasets from internal and external sources – the question arising is whether banks are using adequate analytics to gain value from big data. Big data has been used in banking for some time, mostly in the marketing field, but the usage of big data in banks’ risk management has not been a subject of extensive scientific research. The goals of this paper are twofold. Firstly, the authors are presenting an overview of existing research on the topic of big data usage in banks’ risk management by discussing selected aspects of this topic. Secondly, the authors are formulating a proposal on how to strategically use big data in risk management in banks by merging literature based extracted usage of big data with risk management phases. Expected contributions of this paper are systematizati...
Safety and Reliability, 2016
Big Data can help overcome various problems that exist in present risk analysis practices. By analysing systems as a whole, it is no longer necessary to define in advance what a failure is and what a success is. It is also possible to evaluate how factors that are considered to promote success can combine into catastrophic failures. Big in Big Data is relative. What was called big data 25 years ago is now called small. The continuous development of analysis techniques over the years have resulted in several operational models that use the concept of Big Data. They will become better as the technology and the accessibility of data further improves. With this new generation of systems models, accidents and incidents do not have to wait for analysis to after the fact. They can be studied beforehand in a model. Replacing hindsight by foresight can help to make the world safer, if we desire to do so.