Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2017 | Book

News Sentiment Impact Analysis (NSIA) Framework Read chapter Read first chapter

Enterprise Applications, Markets and Services in the Finance Industry

8th International Workshop, FinanceCom 2016, Frankfurt, Germany, December 8, 2016, Revised Papers

Editors: Stefan Feuerriegel, Dirk Neumann

Publisher: Springer International Publishing

Book Series : Lecture Notes in Business Information Processing

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

This book constitutes revised selected papers from the 8th International Workshop on Enterprise Applications, Markets and Services in the Finance Industry, FinanceCom 2016, held in Frankfurt, Germany, in December 2016.
The 2016 workshop especially focused on “The Analytics Revolution in Finance” and brought together leading academics from a broad range of disciplines, including computer science, business studies, media technology and behavioral science, to discuss recent advances in their respective fields.
The 9 papers presented in this volume were carefully reviewed and selected from 13 submissions.

Table of Contents

Frontmatter
News Sentiment Impact Analysis (NSIA) Framework
Abstract
News analysis activities have been the focus of many research studies across various life domains. So often, the goal of these studies is to automatically, analyze the meaning of news, and to gauge their impact on a particular domain. In this paper, we focus on studying sentiment analysis impact, on financial markets. Current studies, lack systematic approaches to evaluate the impact of a given sentiment dataset, in different financial contexts. We introduce a framework that encompasses models, processes, and a supporting software architecture for defining different financial contexts and conducting sentiment data-sets evaluation. The paper, describes a prototype implementation of the framework and a case study, which investigates the efficacy of the framework in evaluating the impact of a particular news sentiment dataset. The results demonstrate the capability of the framework in bridging the gap between producing a sentiment dataset and evaluating its impact in various financial contexts.
Islam Qudah, Fethi A. Rabhi
A Semantic-Based Analytics Architecture and Its Application to Commodity Pricing
Abstract
Over the past decade, several sophisticated analytic techniques such as machine learning, neural networks, and predictive modelling have evolved to enable scientists to derive insights from data. Data Science is characterised by a cycle of model selection, customization and testing, as scientists often do not know the exact goal or expected results beforehand. Existing research efforts which explore maximising automation, reproducibility and interoperability are quite mature and fail to address a third criterion, usability. The main contribution of this paper is to explore the development of more complex semantic data models linked with existing ontologies (e.g. FIBO) that enable the standardisation of data formats as well as meaning and interpretation of data in automated data analysis. A model-driven architecture with the reference model that capture statistical learning requirement is proposed together with a prototype based around a case study in commodity pricing.
Ali Behnaz, Aarthi Natarajan, Fethi A. Rabhi, Maurice Peat
Detecting Underwriters Stabilisation Trades: A Clinical Study
Abstract
In this study, we examine the stabilisation trades of United Rusal Company IPO’s shares listed on the Hong Kong Stock Exchange (HKEx) and of its Global Depository Shares (GDS) that were simultaneously listed on Euronext Paris. Using both Thomson Reuters Tick History data and the HKEx rules and regulation relating to stabilisation, we identify and analyse the trades that were very likely to have been executed by the stabilisation manager (Credit Suisse) on both markets. We identify nearly 95% of the stabilisation trades on the Euronext Paris, with somewhat less accurate results for Hong Kong. Our results show that the stabilisation trades generated a profit equivalent to about 2.72% of the gross proceeds for the two lead underwriters, a profit which is bigger than their total underwriting commission of 2.31%.
Qudamah Quboa, Brahim Saadouni, Azar Shahgholian, Nikolay Mehandjiev
Predicting Corporate Credit Ratings Using Content Analysis of Annual Reports – A Naïve Bayesian Network Approach
Abstract
Corporate credit ratings are based on a variety of information, including financial statements, annual reports, management interviews, etc. Financial indicators are critical to evaluate corporate creditworthiness. However, little is known about how qualitative information hidden in firm-related documents manifests in credit rating process. To address this issue, this study aims to develop a methodology for extracting topical content from firm-related documents using latent semantic analysis. This information is integrated with traditional financial indicators into a multi-class corporate credit rating prediction model. Informative indicators are obtained using a correlation-based filter in the process of feature selection. We demonstrate that Naïve Bayesian networks perform statistically equivalent to other machine learning methods in terms of classification performance. We further show that the “red flag” values obtained using Naïve Bayesian networks may indicate a low credit quality (non-investment rating classes) of firms. These findings can be particularly important for investors, banks and market regulators.
Petr Hajek, Vladimir Olej, Ondrej Prochazka
Say It at the Right Time: Publication Time of Financial News
Abstract
By law, stock-listed companies must immediately disclose any information that might influence the valuation of the company in order to ensure a fair supply of information to all interested parties. However, laws and regulations do not specify clear requirements regarding the language used and the exact timing when information may be considered relevant enough for disclosure. Previous research shows that delaying bad news provides more time to adjust the language of an announcement in order to encourage a more optimistic perception. This paper investigates how the positive or negative character of news content influences the daily timing of the announcement and how the timing relates to stock performance. We find that negative messages are slightly longer than positive ones. In addition, announcements released before trading tend to have a more positive sentiment than those released during intraday trading, which may reflect a longer preparation time.
Dorina Palade, Simon Alfano, Dirk Neumann
FinTech Transformation: How IT-Enabled Innovations Shape the Financial Sector
Abstract
FinTech, the phenomenon which spans over the areas of information technologies and financial innovation, is currently on the rise and is gaining more and more attention from practitioners, investors and researchers. FinTech is broadly discussed by the media, which constitutes its understanding and represents social opinion, however, this perception of FinTech should be supported by empirical evidences. Therefore, we examine five Swiss FinTech companies through the lens of the conceptual framework of understanding of FinTech and its dimensions and, by doing so, analyze the nature of FinTech innovations. Thereby, we extend the understanding of FinTech and provide a fruitful soil for further research in this area.
Liudmila Zavolokina, Mateusz Dolata, Gerhard Schwabe
Reading Between the Lines: The Effect of Language Sentiment on Economic Indicators
Abstract
Given the ever-increasing volume of information in financial markets, investors must rely on aggregated secondary data sources. Such data sources include indices such as the Ifo Business Climate Index in Germany or the Purchasing Manager Index (PMI) in the United States. However, such indices typically require one to interview experts and are thus cost-intensive and only published with a certain time lag. In contrast, we suggest evaluating the role of sentiment encoded in the mandatory, stock-relevant disclosures of stock-listed companies on various economic indicators. Such sentiment analysis builds on primary information, which covers a large share of the economy, comes at little cost and can reflect new information instantaneously. Our results suggest that such a sentiment analysis explains moves in stock indices and macroeconomic factors, namely the new order flow and unemployment rate.
Florian Förschler, Simon Alfano
Cashless Society: When Will Merchants Stop Accepting Cash in Sweden - A Research Model
Abstract
Over the past decades, we have witnessed changes into how individual’s pay. In particular, there has been a drop in the use of cash as payment instrument both in terms of value and frequency. Consequently, the amount of outstanding cash is shrinking. For instance, in Sweden the level of cash is around 1.5% of Gross Domestic Product. This might be a tipping point for when cash is of practical use. In the paper, we present a research model that explores when merchants will stop accepting cash.
Niklas Arvidsson, Jonas Hedman, Björn Segendorf
Credit Scoring and the Creation of a Generic Predictive Model Using Countries’ Similarities Based on European Values Study
Abstract
Starting with a new product in a new market brings companies a lot of risks and costs. There are companies, who can provide generic scoring models, but usually the accuracy of generic models is not sufficient and they are expensive. The possibility to create a generic predictive model based on a similar country model has been studied. The European Values Study and GESIS Data Archive have been used for research and the similarity coefficient has been calculated and used in the model. The results show that it is possible to build a new model using data from another, similar country and thus minimize costs and risks.
Erika Matsak
Backmatter
Metadata
Title
Enterprise Applications, Markets and Services in the Finance Industry
Editors
Stefan Feuerriegel
Dirk Neumann
Copyright Year
2017
Electronic ISBN
978-3-319-52764-2
Print ISBN
978-3-319-52763-5
DOI
https://doi.org/10.1007/978-3-319-52764-2

Premium Partner

    Image Credits