Machine Learning and Network Analytics in Finance Minitrack
Permanent URI for this collection
This minitrack covers contributions on the use and extension of machine learning and network analytics in financial and econometric analysis. Advanced analytics has been present in the finance literature for decades. However, as a result of developments in the last 15 years, such as the emergence of technological advances and the 2008 financial crisis, the importance of contributions utilizing these techniques have increased significantly. In recent years, it has become crucial to be able to tackle problems in the financial context involving an unprecedented amount of both structured and unstructured data. Likewise, the past financial turmoil with global repercussions has stimulated an interest in advanced approaches for systemic risk measurement. Machine learning and network analysis techniques offer tools for the analysis of a wide range of topics in interconnected financial markets. The purpose of this minitrack is to disseminate significant results on new models relying of machine learning and network analytics, together with relevant and important applications of these models. The scope of the potential contributions to the minitrack is broad and covers most recent advances in analytics, big data, visual analytics, soft computing and network analytics in a financial context.
The topics covered by the minitrack include (but are not limited to):
- Predictive analytics including firm and country-level early-warning indicators and models
- Network analysis, contagion models and topology hierarchies in financial markets
- Systemic risk measures and financial stress indices
- Stress-testing, scenario analysis and simulation
- Text analytics for semantic and sentiment analysis
- Machine learning in portfolio optimization, value at risk and overall risk management
Minitrack Co-Chairs:
Peter Sarlin (Primary Contact)
Hanken School of Economics, Finland
Email: peter@risklab.fi
József Mezei
Åbo Akademi University, Finland
Email: jmezei@abo.fi
Browse
Recent Submissions
-
ItemWhat do they mean? Using Media Richness as an Indicator for the Information Value of Stock Analyst Opinion regarding post-earnings Firm Performance( 2017-01-04)In this research the impact of media-richness on the investor reaction to earnings announcements is investigated. To this end, unstructured (high-richness) sources of analyst opinion are subjected to text-mining and combined with structured (low-richness) sources of analyst opinion, as well as other commonly used structured data relevant to company performance. Results indicate that equivocality is a major problem faced by investors, while uncertainty as understood by media-richness theory appears to be less dominant.
-
ItemPossibilistic Clustering for Crisis Prediction: Systemic Risk States and Membership Degrees( 2017-01-04)Research on understanding and predicting systemic financial \ risk has been of increasing importance in the recent \ years. A common approach is to build predictive models \ based on macro-financial vulnerability indicators to \ identify systemic risk at an early stage. In this article, we \ outline an approach for identifying different systemic risk \ states through possibilistic fuzzy clustering. Instead of directly \ using a supervised classification method, we aim at \ identifying coherent groups of vulnerability with macrofinancial \ indicators for pre-crisis data, and determine the \ level of risk for a new observation based on its similarity \ to the identified groups. The approach allows for differentiating \ among different possible pre-crisis states, and \ using this information for estimating the possibility of systemic \ risk. In this work, we compare different fuzzy clustering \ methods, as well as conduct an empirical exercise \ for European systemic banking crises.
-
ItemHow The Market Can Detect Its Own Mispricing - A Sentiment Index To Detect Irrational Exuberance( 2017-01-04)The emergence of big data analytics enables real \ time news analysis. Such analysis offers the possibility to instantly \ extract the sentiment conveyed by any newly published, \ textual information source. This paper investigates the existence \ of a causal relationship between news sentiment and stock \ prices. As such, we apply news sentiment analysis for unstructured, \ textual data to extract sentiment scores and utilize \ the Granger-causality test to determine the causal relationship \ between daily news sentiment scores and the corresponding \ stock market returns. Upon successfully identifying such a \ causal relationship with a time lag, we develop a real-time \ news sentiment index. This news sentiment index serves as \ a decision-support system in detecting a potential over- or \ undervaluation of stock prices given the news sentiment of \ available news sources. Thus, as a novelty, the news sentiment \ index serves as an early-warning system to detect irrational \ exuberance.
-
Item