Bringing Financial applications of Sentiment Analysis to India and Hong Kong

In March 2017, OptiRisk were proud to have partnered with Indian Institute of Management Calcutta and UNICOM seminars to present at two conferences in Asia:

AI, Machine Learning and Sentiment Analysis Applied to • Financial Markets • Consumer Markets
8-9 March 2017, Bangalore, India

In India, we were hosted by Indian Institute of Management Bangalore where OptiRisk kicked off the two day conference with a presentation on uses of sentiment analysis in Finance. Sat in the audience were curious minds from academia, industry and fintech start-ups all keen to understand the power of machines and algorithms. Indeed they were not disappointed with the content delivered at this event.

This conference explored the uses of AI in both the financial markets and consumer/retail markets by addressing these industries in different streams. Highlights of talks in the consumer/retail stream include speakers from IBM, AIG and MakeMyTrip. All these speakers seamlessly joined together the significance of text analytics, natural language processing and machine learning to their respective business objectives, i.e. gauging consumer sentiment, constructing cutting edge business management directives and breaking down barriers with open source technologies.

On the financial application side of things, sentiment analysis was more of a hot topic with Prof Ashok Banerjee presenting on the prediction of defaults in Indian banks using sentiment extracted from annual reports. Nitish Sinha (Federal Reserve Board USA) presented his work on prediction of stock price returns using news stories and studied the effect at different frequencies. The panel session on day 2 invigorated conversations even more due to the divided opinions expressed by panellists. After all, this is the desired effect of a panel discussion!


(Vivek Bajaj, Founder of StockEdge, presenting in Bangalore, India)

AI, Machine Learning and Sentiment Analysis Applied to Finance
14-15 March 2017, Hong Kong

The conference in Hong Kong was a congregation of researchers and practitioners from local institutions as well as foreign countries. The event kicked off with a brilliant overview presentation by Prof Pascale Fung from HKUST, which led the way for the following presentations on these topics. Risk management and stock price prediction were all covered as well as sentiment analysis using unofficial news sources such as microblogs and social media feeds – in Chinese and in English.


(Panel discussion with Prof Gautam Mitra (Moderator-right), Prof Asher Curtis, Prof Svetlana Borovkova, Prof Enza Messina and Prof Pascale Fung.)

Overall, these two conferences were a resounding success, where many ideas were exchanged and connections were made. So much so that OptiRisk are committed to taking part again next year – watch this space!

Presentation slides are available upon request. Please contact info@unicom.co.uk.

Posted in Workshops and Seminars | Leave a comment

US Elections- Sentiment Analysis gets it right again!

The recent US Election has been a roller coaster ride. Perceptions towards candidates continuously fluctuated following every interview, debate and allegation. We have gathered some information from our friends at RavenPack and Amareos to show how sentiment analysis predicted the election.

Through this election as well as Brexit voting, we have definitely learnt that polls aren’t as reliable as they used to be. What is coming to light though, is the definite growing importance of sentiment analysis. Sentiment Analysis aggregates data from many media platforms (editorial news, commentary and social media all included) and depicts the thought processes of its authors. In these two historical political moments, sentiment analysis has proven to be more accurate than polls. Amareos predicted Trumps victory based on crowd sourced data from twitter sentiment.

3- Day rolling Average for Sentiment Spread vs polls spread

RavenPack conducted a media sentiment study of the elections for a 14- day and a 3- day rolling average for sentiment spread vs polls spread. The poll numbers have been extracted from the Financial Times and RavenPack has calculated average sentiment levels on a daily basis across various categories for each candidate to deduce the sentiment spread. Numerous ups and downs have been seen during these elections and those evidently impact the public opinion of the candidate as seen in the graph above. Clinton was leading before Director Comey reopened the investigation on Mrs. Clinton on October 28th. And then on November 6th, once the FBI cleared her of all charges, the sentiment was leaning in her favor again as indicated by the graph above.

Now that the elections have come to an end, Trumps victory has brought uncertainty to the Global Financial Markets. This is simply because we don’t know what kind of president Trump will be. Will he be the erratic person who threatened to lock up his political rivals during the campaign? Or is he capable of being a rational leader of the free world?

Posted in Uncategorized | Leave a comment

New Developments in IT and Finance Innovation

Last week OptiRisk Systems took part in exclusive conferences held on 14th and 15th July on the topics of:

1. AI, Machine Learning and Sentiment Analysis Applied to Finance
and
2. Blockchain: Distributed Ledger and Financial Services

OptiRisk Systems exhibited at the conferences organized by UNICOM Seminars. Prof Gautam Mitra, CEO of OptiRisk Systems, was the Chairperson for the event as well as the extensive panel discussion based on the topic of Adoption of Sentiment Analysis, AI & Machine Learning in trading strategies and risk control. Among the panelists were Elijah DePalma and James Cantarella, Thomson Reuters; Pierce Crosby, StockTwits; Anders Bally, Sentifi; Peter Hafez, RavenPack; Stephen Morse, Twitter.

Xiang Yu and Tilman Sayer from OptiRisk Systems talked about how to Beat Markowitz with Sentiment and the Downside Risk Control. The talk described an innovative and dynamic trading strategy for equities, with a particular focus on controlling downside risk. They explained the mathematical concept behind the approach – stochastic dominance, and depicted the advantages of making investment decisions are based on distributions rather than moments. A major contribution of news sentiment, in their research, is in the prediction of future volatility. Regression analysis on news sentiment and regime switching models are employed to digest market moods and account for changing market situations.

OptiRisk Systems is continuously researching in the field of Sentiment Analysis and finance. For continuous updates on our research and developments, follow us on Twitter and LinkedIn

Posted in Uncategorized | Leave a comment

BREXIT: Human Behavior impacts financial markets

Human behavior and actions lead to Extreme events which have ‘Big’ political, economic, social and technological impacts on the global financial markets. Merve Alanyali and Tobias Preis are thought leaders in this domain; they explain the journey from News to protests: how human behaviour around the world impacts financial markets.

Tobias Preis is an Associate professor of Behavioral Science and Finance at the University of Warwick and the owner of Artemis Capital Asset Management.

Merve Alanyali is a PhD candidate at Warwick Business School and her research focuses on using Machine learning to understand and predict human behavior on a global scale.

Cognovi Labs successfully and correctly predicted the results of the EU referendum with the help of Sentiment Analysis. The tool predicted the Brexit nearly six hours prior to the results were annouced by analysing Tweets thorugh Twitris Tool. Today, Twitris uses only Twitter as a data source but Cognovi labs intends to include other social media and network sources to analyse sentiment and determine future outcomes and patterns. Click here to know more.

Register for the AI, Machine Learning and Sentiment Analysis in Finance conference to stay ahead and know the most current and lastest research on the topic of Sentiment Analysis.

Posted in Uncategorized | Leave a comment

Unchained value: Can blockchain be a security enabler?

The world has changed. Cyberspace and the security of it is now critical to both the civil and economic wellbeing of almost all developed and developing nations. New ways of working have enabled significant productivity gains to be realised, especially in areas of commerce and social media. The ability for us to transact across the globe has afforded us access to consumers and areas previously unreachable by traditional technology.

Cyber security has, in some respects, been an inhibitor to development and in some cases a blocker in our corporate, personal and civic lives. This is no more apparent than the centralised security solutions we have created, such as authentication, authorisation and verification technologies. These centralised ways of working are at odds in the way we as humans operate, yes we need (indeed crave) structure, however a over burdening of structure can stifle innovation, and lead to ingenious Robosapiens looking for ways around the security controls put in place.

As we live in a framework society, governed by laws, ethical rules and regulations we should try to adopt a framework approach to cyber security, that affords us the ability to do our work, live our lives yet prosecute wrong doer’s if they deviate from acceptable norms. Technologies such as block chains and peer-to-peer technologies may provide this type of framework control, whereby we as clever users don’t feel the need to look for holes as the system doesn’t get in the way.

Blockchains are by their nature, distributed and decentralised and therefore may provide a new way to move to a real framework society. Coupling this technology to the recent developments cloud, fog and IoT computing, the 2010’s are shaping up to be a very interesting time for us!

Written by: Paul Lewis.
Paul is responsible for strategic commercialisation, technical strategy and research lead product development within Crossword, alongside delivery of new service lines.
He has over 15 years’ experience of working within IT and cyber security. His experience includes technical and senior management positions, most recently at the Defence Academy of the United Kingdom (Cranfield University). Prior to this, Paul was a senior policy advisor to the UK Dept for Business, Innovation and Skills.

Paul Lewis is one of the speakers in the Blockchain: Distributed Ledger and Financial services conference, London, July 2016. Register now

Posted in Uncategorized | Leave a comment

OptiRisk at the APMOD conference, 2016

OptiRisk Systems sponsored and participated at the 12th International conference on Applied Mathematical Programming and Modelling that was held in Brno, Czech Republic on June 8-10, 2016. OptiRisk team presented on various topics during the conference:

OptiRisk will soon be presenting in the International Conference on Stochastic Programming . If you have missed us in Brno, catch us in Brazil!

Posted in Uncategorized | Leave a comment

OptiRisk at the Data Analytics and Sentiment Analysis conference

During the Data Analytics conference held on 14 April 2016, in London, Tilman Sayer from OptiRisk Systems shed light on the topic ‘ Combining sentiment data and market data to enhance financial analytics applications.’

He talked about how sentiment data can impact daily trading strategies and has the power to enhance financial mathematical models for trading purposes according to his joint work with Cristiano Arbex-Valle, Gautam Mitra & Xiang Yu. He briefly explained how we create the news impact scores. The impact is used to enhance volatility (and liquidity) prediction while the SSD reduces negative risk and increases positive potential. He further discussed how the combined effect of volatility and SSD leads to enhance dynamic trading strategies.

To know more about this presentation and Sentiment Analysis in Finance, follow OptiRisk systems on LinkedIn.

Posted in Uncategorized | Leave a comment

Launch of the “Handbook of Sentiment Analysis in Finance”

Building on the success of The Handbook of News Analytics in Finance, the editors (Prof.Gautam Mitra and Dr. Xiang Yu) have researched and compiled this new volume: “Handbook of Sentiment Analysis in Finance”. The Handbook was launched on 10 March 2016 in Singapore, with many of the contributors being present at the event.

In the last four years there has been explosive developments in the domain of sentiment analysis in general and sentiment classification in particular. There has been a growing consumer interest in social media and these new media sources have become the leading ‘influencers’ of market sentiment.

The latest version of the Handbook provides the current developments in Sentiment Analysis in Finance. The topics covered include:
1.Text analytics and Sentiment Classification
2.Online Search and Social Media sources
3.Sentiment Analysis applied to Equity
4.Sentiment Analysis for other Asset Classes: Energy, Commodities, Green Commodities, Bonds and FX
5.Use of Sentiment Analysis in Daily and High Frequency Trading
6.Applications of Sentiment Analysis: Case studies

To order your copy, mail info@optirisk-systems.com today.

Posted in Uncategorized | Leave a comment

Sentiment Analysis in Finance, Singapore 2016.

The world is now connected to news and information everywhere, narrowing the gap between locations and accelerating the speed of information processing. Data scientists and financial experts are trying to catch up with these evolutions by automating the extraction of sentiment from news. In simpler words, Sentiment Analysis is used to understand the reaction of a person or a group of people to a particular news item. Sentiment analysis is an emerging area where structured and unstructured data is analyzed to generate useful insights leading to improved performances. Information obtained from multiple sources including news wires, macro-economic announcements, social media, micro blogs /twitter, online (search) information such as Google trends and Wikipedia influence both business intelligence and performance evaluation. This sentiment data can help investors and finance professionals to exploit the market and manage their risk exposure.

There is continuous research on this topic by experts all over the world and therefore development in this field is also fast gaining momentum in the Finance industry. During the conference, Prof Tobias Preis, of University of Warwick, answered two questions. The first, can big data resources provide insights into crises in financial markets and the second, can we provide insight into international differences in economic wellbeing by comparing patterns of interaction with the Internet?

In the ‘Handbook of Sentiment Analysis in Finance,’ Professor Gautam Mitra has described a model by which we can measure the impact of sentiment. This handbook was also launched on the 10th of March during the conference on Sentiment Analysis in Finance in Singapore, where many contributors were also present.

Focusing on social media, Prof Enza Messina, co-founder of Sharper Analytics, researches into Twitter and carries out text and network analysis for sentiment mining. Sharing her research results, she discussed how social relationships can be managed to improve user-level sentiment analysis of micro blogs. Weibo (the Chinese equivalent to Twitter) has also been studied to find out sentiments within China. The Chinese equity market has seen an increase in the number of retail investors in recent years, raising interest for Eric Tham, Director of Quantitative Strategies at iMaibo. Analysing two sources of domestic online media-news and social blogs media- Eric determines the factors that have led to this change and discussed the same during the conference.

Commodity trading is yet another application for sentiment analysis, as it is important to understand whether news sentiment affects commodity prices and if yes, how do they do so? Answering this question in her talk, Svetlana Borovkova explained how to make profitable trading strategies and avoid the downside.

Ashok Banerjee, Departmental Head of Finance and Control, explained how the research in the Finance lab of IIM Calcutta has shown that the effect of any news on financial markets depends on the attention of investors. This follows the simple logic that processing any attention-grabbing event requires effort and in absence of that effort (Attention), data (Sentiment) can be missed. Elijah DePalma of Thomson Reuters shed light upon his findings with working on sentiment for the Japanese language.

To obtain conference material, contact us on info@optirisk-systems.com

Posted in Uncategorized | Leave a comment

Behavioural Models & Sentiment Analysis Applied to Finance Conference 2014

Sentiment Analysis and the related topic of Opinion Mining concerns the analysis of texts (news, social media, micro blogs) and turning these into sentiments, opinions even feelings and human emotions.  This goes beyond simply analysing the number of likes, shares or comments we normally get after any marketing campaign and then reviewing it for the number of positives, negatives and measuring the level of success.

Sentiment Analysis is definitely creating waves in the finance sector. UNICOM organised on 18 – 19 June 2014,  a very engaging Conference : Behavioural Models & Sentiment Analysis Applied to Finance. Major News Analytics vendors including Bloomberg, Thomson Reuters, RavenPack, OptiRisk Systems, Deltix, Northfield Information Services and MarketPsych participated and exhibited in the conference. The conference was based on four sections: Foundations & Technologies of Sentiment Analysis for Finance; Sentiment Analysis for Finance: Case Studies & Use Cases; Social Media, Micro Blogs, Google Trends; Sentiment Analysis for Multiple Asset Classes.

In this event, UNICOM brought together a unique group of industry researchers and academic whose work is exclusively focused in this domain. Over 145 professionals from the finance industry attended the conference.

Tobias Preis from Warwick Business School & Artemis Capital Asset Management Gmbh was an Opening Keynote. In his talk, he outlined some recent highlights of his research and presented “Quantifying Economic Behaviour Using Big Data”.

A research work on “Evolution of News Analytics” was presented by Gary Kazantsev,  Head of R&D Machine Learning Group at Bloomberg. He highlighted Sentiment Analysis in broader way and presented better models for short texts (headlines, twitter etc) and Market Impact Indicators (Market Moving News).

Elijah DePalma, Senior Quantitative Research Analyst from Thomson Reuters introduced News Analytics and Text Analytics, Firm Level Sentiment, Market-wide Sentiment in his agenda of presentation. In his talk “Sentiment and Investors Behaviour” he shared Thomson Reuters News Archive data from 1996 – present.

Exploiting Entity Co-referencing in Unstructured News was explained by Peter Hafez, Director of Quantitative Research at RavenPack. Peter outlined Multi-dimensional predictive modelling and the impact of news across company “networks”.

Gautam Mitra, Managing Director of OptiRisk Systems showed results of News Stories: Measuring the impact on Asset Behaviour and Designing Trading Strategies. He first introduced a new metric “news impact” which combines: sentiment, decay of sentiment over time, and the volume of news. Then he presented an outline of how the concepts of log optimal growth and ‘volatility pumping’ can be introduced in news enhanced trading strategies.

An Automated Trading Strategy for Equities Using Crowd-Sourced Earning Data was described by Ilya Gorelik from Deltix. He explained well the implementation of an automated equity trading strategy based on aggregated company earnings estimates sourced from independent, buy-side and sell-side analysts, along with those of private investors.

Day two of the conference was opened by Stephen Pulman, Professor of Computational Linguistics, Oxford University / TheySay (Analytics). The keynote speaker highlighted “Compositional Sentiment Analysis”.

Louis Scott, Northfield Info Services Inc and Founder of Kiema Advisors presented “Sentiment, News and Volatility in both Stock Returns and Trading Volume”. He explained well, how Northfield uses alternative paradigm to examine the role of sentiment analysis.

Social Media Analytics Applied to Finance was explained well by Sri Priya Ponnapalli from Bloomberg. She discussed as social media is moving into the financial sphere, Bloomberg can evaluate the opinions about traded instruments and track news and sentiment with respect to e.g. equity issuing companies in real-time.

Another  interesting aspect of the conference were the panel discussions spread over three panels: Panel 1:- Adoption of Sentiment Analysis in Fund management & Trading Strategies, moderated by Gautam Mitra from OptiRisk Systems; Panel 2:- Use of News and Social Media Data for Market Surveillance & Operational Risk Control, moderated by Ashok Banerjee from IIMCal; Panel 3:- Data Sources: Market Data, News (Meta) Data, Social Media Data, Google Trends & Others, moderated by Andrew Rummer from Bloomberg. The panels engaged the participants in engaging interactive discussions.

Bing Liu, a Professor and subject expert from University of Illinois at Chicago delivered the closing keynote talk: “Sentiment Analysis: Past, Present and the Future”.

OptiRisk a company specialising in financial analytics is compiling the update of their Handbook of News Analytics in Finance.  Contributions are solicited for the New Handbook: Sentiment Analysis Applied to Finance. Please see the link for more information: News Analytics Handbook

Also the conference recordings and the slides can be obtained by making email requests to:  aqeela@unicom.co.uk.

We thank all the active participants of the conference in particular a big thank you to our sponsors Bloomberg, Thomson Reuters, RavenPack, OptiRisk Systems, Northfield Information Services, Deltix.

UNICOM is planning the repeat event “Behavioural Models & Sentiment Analysis Applied to Finance” in summer of 2015 in London. ..WATCH THIS SPACE.

 

Posted in Uncategorized | Tagged , , , , | Leave a comment