Ashok Banerjee,IIM Calcutta
Research at Finance Lab of IIM Calcutta, shows that the effect of any news on the market depends on the attention of investors. If the attention of investors were somewhere else, even news carrying strong positive/negative sentiment would go unnoticed or would be penalized. This is particularly true in the case of major non-market attention grabbing events. In other words, attention overwhelms the effect of sentiment. Processing any attention-grabbing event requires effort. If that effort is directed towards particular information, people are reluctant to make the extra effort to process any other information at the same time, no matter how much sentiment that information might carry.
Gautam Mitra, OptiRisk Systems
Sentiment Analysis is emerging as an important soft technology tool that is influencing Business Intelligence and Performance Evaluation as these are practised in industry and commerce today. In this talk we first introduce the multiple sources of information, namely, News Wires, Macro-economic Announcements, Social Media, Microblogs/Twitter, Online (search) Information such as Google Trends and Wiki. We then describe a model by which we measure the impact of these and finally how this impact measure is used to improve the predictive models of asset behaviour.As our aim is to improve the ‘ALPHA’ of our trade portfolios we describe strategies by which we make choices for asset allocation. In particular we describe how to apply Second Order Stochastic Dominance for asset allocation and combine this with Kelly’s strategy for money management.
Tobias Preis, Warwick Business School
In this talk, I will outline some recent highlights of our research, addressing two questions. Firstly, can big data resources provide insights into crises in financial markets? By analysing Google query volumes for search terms related to finance and views of Wikipedia articles, we find patterns which may be interpreted as early warning signs of stock market moves. Secondly, can we provide insight into international differences in economic well being by comparing patterns of interaction with the Internet? To answer this question, we introduce a future orientation index to quantify the degree to which Internet users seek more information about years in the future than years in the past. We analyse Google logs and find a striking correlation between the country's GDP and the predisposition of its inhabitants to look forward. Our results illustrate the potential that combining extensive behavioural data sets offers for a better understanding of large scale human economic behaviour.
Svetlana Borovkova, Vrije Universiteit Amsterdam
In this presentation, we address the issue of trading commodities on the basis of news sentiment. First, we outline the effects of news sentiment on the prices of different commodity futures. Profitable sentiment-based trading strategies are then constructed for individual commodities, with the eventual goal of building a profitable multi-commodity diversified trading strategy. The news sentiment is extracted from the Thomson Reuters News Analytics Engine (TRNAE) and the traded commodities are the constituents of the Dow Jones Commodity Index (DJCI). We show that profitable sentiment-based trading strategies can be constructed, which show consistent good performance for various commodities as well as for commodity portfolios. We analyse the strategies also in terms of risk profiles and show how the downside can be limited.
Enza Messina, University of Milano-Bicocca
In this talk we show how social relationships can be managed to improve user-level sentiment analysis of microblogs, overcoming the limitation of the state-of-the-art methods that generally consider posts as independent data. We show how combining post contents and network structure information may lead to significant improvements in the polarity classification of the sentiment both at post and at user level.
Eric Tham, iMaibo
The Chinese equity market has seen an increase in the number of retail investors in recent years. In this talk, sentiment analysis of two sources of the domestic online media are considered - news and social blogs media. This is captured through a NLP of the Chinese language by carefully selecting financial idioms and supervised learning. Results show a statistically significant lead-lag relationship between the news media sentiment and the Shanghai Stock index (SSE) that is indicative of momentum strategies. The social media sentiment displays a strong contemporaneous relationship with SSE returns. This contemporaneous relation is modelled through a state space model reflecting the volatile sensitivity of the market returns to social media sentiment.
10th–11th March 2016