Project: News Optimised Risk Management
Towards a new financial paradigm: behavioural finance with news optimised risk management_x000D__x000D_In today's chaotic financial climate, systems for predicting market behaviour and attitudes of financial professionals are under scrutiny. Current market risk assessment characteristics disregard market information that is available from additional sources like, for example, financial news. There are whole new possibilities for producing meaningful market behaviour models by incorporating behavioural and quantitative finance, using the latest techniques and powerful modelling tools. The prevailing market environment can (to some extent) be captured by key innovative techniques of news analytics that quantify news sentiments. The emergence and impact of such behavioural finance is illustrated by the 4-5 Nobel Prizes for Economics awarded in this field in recent years._x000D__x000D_This project proposals sets out to improve current risk assessment practices by accurately identifying significant changes in market conditions by using automatic semantic analysis of current financial news streams. The proposed end result is a proof of concept application that uses real time financial news to calculate a more relevant and more reliable risk metric. _x000D__x000D_The problem of incomplete information in Market Risk Assessment_x000D__x000D_Financial risk management is important since it enables companies to identify risks or to anticipate potential risks before they occur, thereby possibly preventing companies from potential disasters or minimizing their effects._x000D__x000D_Market risk assessment constitutes a significant part of the estimation of financial risk and is calculated using risk measures and expressed in risk metrics and has traditionally been estimated by using historical data. This has the disadvantage that it provides a retrospective indication of risk, which may not be a proper indication of current and future risk with instable market conditions. Currently, popular measures used for estimating market risk are the Value at Risk (VaR) and the Expected Shortfall (ES) metrics. It is vital for companies to know about risks at the moment that decisions are made, and VaR or ES enable this by incorporating future prospectives into their risk calculation by using probability distributions. However, classical VaR calculation assumes that only the risk of the single assets and their correlation (or dependence) matters. It does not take sudden market changes into account. As a consequence, this makes the VaR inflexible and unresponsive with regard to abnormal market conditions, such as with the instability caused by high-impact news events or an economic crisis._x000D__x000D_Refining VaR and ES calculation using Semantic News Analysis_x000D__x000D_Abnormal market conditions exert a much higher risk than normal market conditions and it is therefore vital to include them in risk management strategies. The inflexibility of market risk measures with regard to such abnormal conditions can be countered by developing a system that takes financial news messages into account. Financial news reports all events that are relevant for the value of an equity. Such events, or chains of such events, might cause instable market conditions. Detection of these events can be used to estimate the probability of emerging abnormal market conditions. By incorporating news into the risk calculation, sudden impactful events can help to determine the kind of distribution that should be attributed to individual parameters of the calculation. In order to do so, news messages need to be given an impact-value._x000D__x000D_The implementation of Semantic News Analysis_x000D__x000D_In order to use news as a source for a certain market risk evaluation, it needs to be determined what the impact of news items is on the equities of portfolios in that specific market. Recent technological developments have enabled the creation of data-mining tools that can interpret live news feeds. Combining such technologies with risk metrics, such as VaR could lead to quicker, more flexible and more accurate risk assessment calculation._x000D__x000D_Historical data can be analysed to determine the magnitude of specific events or event combinations. This would yield an estimate of the probability that abnormal market conditions occur. It would also result in an estimate of the effect of the instable market behaviour on a certain equity. As such, news event analysis could be used as input for risk measures to calculate risk metrics during abnormal market conditions and answer two important questions: Will there be abnormal market conditions? and What will be the effect on a certain portfolio?_x000D__x000D_The project consortium_x000D__x000D_The project consortium consists of five highly innovation-oriented SMEs and a leading, cutting-edge research institute with complementary technical and marketing capacities. The skills of the participants range from news processing automation, ontology- and semantic based technologies, financial mathematics and financial risk management expertise. _x000D__x000D_
|
Acronym
|
NORM
(Reference Number: 5131)
|
|
Duration
|
01/10/2010 - 31/03/2013
|
|
Project Topic
|
This project aims to enhance market risk assessment metrics by using semantically analysed news-based information. This will compensate for inflexibility of existing models with regard to strong market fluctuations or market instability and give more dynamic, more reliable market risk estimation.
|
|
Network
|
Eurostars
|
|
Call
|
Eurostars Cut-Off 3
|
Project partner
