Artificial Intelligence, Machine Learning and Sentiment Analysis are changing the way in which numerous client services are offered. In particular, Financial Organisations are creating and leveraging such innovation in the domain of wealth management. This trend is now being taken on board by multiple innovators: academia, start-ups, technology companies and financial market participants.
AI and Machine Learning have emerged as a central aspect of analytics which is applied to multiple domains. AI and Machine Learning, Pattern classifiers and natural language processing (NLP) underpin Sentiment Analysis (SA); SA is a technology that makes rapid assessment of the sentiments expressed in news releases as well as other media sources such as Twitter and blogs.
The conference addresses and explains how to extract sentiment from these multiple sources of information and showcases the advances that have taken place in the field of financial innovation. The focus is on the latest research and includes presentations by leading subject experts from all over the world, as well as a number of applications/case studies.
Topics to be covered include:
Sanjiv Das, Professor of Finance and Data Science, Santa Clara University, USA
Information is extracted from big textual data to create a single risk score for the financial system. To do this network analysis is overlaid with mathematical theory to create a systemic risk monitoring dashboard. I will discuss implementations in the US and India. Extensions to stochastic networks will also be presented.
Xiang Yu, Business Development Techno Executive, and Gautam Mitra, CEO/Director, OptiRisk Systems/UCL, UK
We have created an innovative and dynamic trading strategy for equities, with a particular focus on controlling downside risk. The mathematical concept behind the approach is called stochastic dominance, where investment decisions are based on distributions rather than moments. A major contribution of news sentiment is in the prediction of future distributions. Regression analysis on news sentiment and regime switching models are employed to digest market moods and account for changing market situations.
Ashok Banerjee, Departmental Head of Finance and Control, Indian Institute of Management, Calcutta (IIMC), India
Banks and financial institutions in emerging markets are saddled with a huge proportion of bad loans. Banking regulations require lenders to provide for troubled debt which adversely affects the profitability of banks. The capital market also reacts negatively to such write-offs of big ticket debts. Banks are, therefore, putting significant resources into developing early warning signals to arrest eventual default. The financial institutions use a wide range of default prediction models to estimate the loan loss. These models use data from financial statements and the market. The present study shows that such models fail to provide effective early warning signals. We use annual reports of companies to develop a default model which is predictive and hence has the capability of providing early warning signals. Using information from Directors' Reports, Audit Reports and notes to accounts, our model successfully discriminates the 'good' firms from the 'bad' ones.
Enza Messina, Professor in Operations Research, University of Milano-Bicocca, Italy
We show how deep learning and ensemble methods can successfully address challenging problems arising in sentiment analysis such as irony detection or domain adaptation. In particular, we propose an unsupervised framework for domain-independent irony detection built upon an existing probabilistic topic model initially introduced for sentiment analysis purposes. Moreover, in order to improve its generalization abilities, we apply Word Embeddings to obtain domain-aware ironic orientation of words. The acquisition of cross-domain high level feature representations through word embeddings combined with the generalization capability of ensemble methods can also be used for addressing the problem of domain adaptation also in the scenario where the testing target domain is completely unlabeled.
Richard Peterson, CEO, MarketPsych Data, USA
Dr. Peterson will describe the unique characteristics of media sentiment data and approaches to financial price prediction with this data. The basics of media sentiment data, various modeling approaches, and their results (including live trading results) will be described in this talk. Viewers will gain an understanding of real-world modeling tips and techniques when dealing with noisy and inconsistent data such as media sentiment streams.
Giuliano De Rossi, Macquarie Research
Recent academic research (and our own work on US data) have found that analyst conference calls convey useful information not contained in earnings numbers and analyst forecasts. The slow reaction of markets to that type of information implies that sentiment, as expressed by analysts and management during the call, predicts returns. This effect is distinct from the well known post earnings announcement drift. We collected call transcripts for global companies from Factset going back to 2002. Using text mining techniques, we measure the tone of the management discussion and Q&A session of each call, with a goal of developing an alpha signal at low frequency. This presentation describes the strategy and findings of our research.
Tilman Sayer, Advanced Logic Analytics
The classic Markowitz model considers the standard characteristics: return and volatility. Second order stochastic dominance (SSD) in contrast encompasses the whole distribution of asset returns.
The true magic of SSD lies in its choice of portfolio based on the minimisation of downside tail risk. Using this modelling paradigm we have developed an innovative and dynamic trading product for equities. News sentiment is integrated into the system to digest market moods and enhance prediction. Regime switching algorithms are used to detect market shifts. We provide insight into these novel techniques and supply performance results.
Roland Schweter, Acatis Research; Joerg Wenzel Fraunhofer Institute for Industrial Mathematics ITWM; Christina Erlwein, OptiRisk Systems; Michael Phringer, PS Quant
We report the outlook of credit risk assessment tool, in which sentiments of news and social media included in the risk assessment of corporate and sovereign bonds. Our tool investigates all current country and company information and market sentiment as well as historical time series to enable a quantitative as well as qualitative analysis of bonds’ inherent risk.
Title: Text Analytics for Sentiment Extraction in Finance with Applications
Speakers: Sanjiv Das, William and Janice Terry Professor of Finance, Leavey School of Business, Santa Clara University, USA
This tutorial will survey the technology and empirics of text analytics in finance. It will cover various tools of information extraction and text analytics for determining sentiment. We will learn a range of techniques of classification and predictive analytics, topic analysis, and metrics used to assess the performance of sentiment algorithms. We will also visit the literature on text mining and predictive analytics in finance, covering a wide range of text sources such as blogs, news, web posts, corporate filings, etc. The R programming language will be used, and various packages therein will be presented.
Sanjiv Das is the William and Janice Terry Professor of Finance at Santa Clara University’s Leavey School of Business. He was previously Associate Professor at Harvard Business School and UC Berkeley. He holds post-graduate degrees in Finance (M.Phil and Ph.D. from New York University), Computer Science (M.S. from UC Berkeley), an MBA from the Indian Institute of Management, and is a qualified Cost and Works Accountant. He edits several academic journals. Prior to being an academic, he worked in the derivatives business as a Vice-President at Citibank. His current research interests include: the modeling of default risk, machine learning, social networks, derivatives pricing models, portfolio theory, and venture capital. He has published over ninety articles in academic journals, and won numerous awards for research and teaching. His recent book “Derivatives: Principles and Practice” was published in May 2010. He currently also serves as a Senior Fellow at the FDIC Center for Financial Research.