Knowsis Offers Social Media Sentiment Data to Support Trading Strategies

Knowsis Offers Social Media Sentiment Data to Support Trading Strategies

Start-up data and analytics firm Knowsis is working with an initial five clients to incorporate its social media sentiment data into their trading strategies. The company declines to name the clients, but says one will go live imminently with strategies built around signals from Knowsis data, while others are considering how to add sentiment data as an additional parameter to their strategies.

London-based Knowsis was formed as a private company in January 2012 with seed investment from Method Investment and Advisory, a funds and quant trading house that Knowsis can also work with to develop and check its concepts. Knowsis’ founder and CEO Oli Freeling-Wilkinson is joined by chief technology officer Mark Unsworth, a technologist and developer most recently working with online music company 7digital, and two further employees.

The company was conceived by Wilkinson in 2010, when there was little financial market recognition of the potential of social media, but he says the question now is no longer whether social media is important, but how to use it. He adds: “Any quantitative trader, hedge fund or risk manager should be interested in data that is proven to help make decisions and money.”

While the company isn’t naming names – its own is based on gnosis, the Greek noun for knowledge – it has worked with quantitative funds to test the use of social media sentiment data in trading strategies. The tests were based on a portfolio of stocks, with each stock being given a sentiment rating based on social media activity and simple trading strategies then being devised. The company says all trading strategies in the test generated returns above those achieved by major indices over the same time period.

Knowsis’ methodology is based on one overarching question: will sentiment make a difference to asset prices? With this in mind, its analysis identifies underlying behavioural trends rather than supporting a ‘trade by tweet’ approach.

The company initially considered using third-party sentiment data systems that are frequently used by large consumer brands to support its service, but found these lacked financial relevance. Instead, it has built technology from the ground up to mine, manage and analyse vast quantities of data produced by social media. It uses scrapers and similar technologies to gather data and filters about 1% of Twitter’s 400 million daily tweets using in-house built algorithms designed to identify Tweets that have financial relevance. It also looks at Facebook, but only to a limited extent as it is a closed system, and scans further blogs and forums that it chooses not to name as it fears malicious activity could skew results. The platform is data agnostic, meaning any social media source could be used to feed the algos and it also includes a machine learning element.

Once data is collected, a sentiment analysis tool is used to aggregate underlying behaviour around an asset and the asset is given a number on the scale of -100 (bearish) to +100 (bullish). A list of securities, predominantly macro assets and some stocks, and their sentiment scores is then made available to users via an application programming interface that is updated in real time, although Knowsis notes the volatility of intra-day conversation and prefers to promote end-of-day aggregated sentiment data that can be validated and checked for false or misleading information.

The company is working across financial markets and includes high frequency, low latency traders that pick up signals in real time, but its drive is towards understanding rather than speed. Wilkinson explains: “Knowsis is not about ultra low latency delivery, but about longer term underlying behaviour trends. The aim is for end-of-day data to be used to project how certain asset classes may behave during the next week.”

With five clients in its portfolio and R&D ongoing, Knowsis’ next plan is a sales push and a search for specialist market data partners that can distribute its social media sentiment data on a global scale.

Progress Software Expands Cloud and On-Premise Data Connectivity Lineup

Progress Software Corporation (NASDAQ: PRGS) today announced new and expanded data sources for its DataDirect Cloud™ service and its DataDirect Connect® family of products.

via Pocket June 28, 2013 at 07:54PM


via Pocket June 28, 2013 at 07:47PM

Q&A: Ian Blance of Six Financial Information on the Importance of Evaluated Pricing

Q&A: Ian Blance of Six Financial Information on the Importance of Evaluated Pricing

Q and A | September 27, 2012 – 9:53am

Ian Blance is head of evaluated pricing business development at SIX Financial Information, a major supplier of valuations and pricing services across global financial markets.

Why are valuations such an important aspect of the data business?

The valuation of assets is fundamental to the functioning of the financial system. Without an appropriate value, mission-critical activities would simply not be possible – fund NAV calculations, client reporting, book P&L, performance measurement, risk measures, company accounts, collateral management … the list is endless.  Many of these valuations are collected or calculated and then disseminated by the data industry, which makes the data vendors key players in this piece of the business. When it comes to exchange-traded asset classes, the collection and delivery of valuation prices is relatively uncontroversial. But when it comes to illiquid or thinly traded instruments, the challenge – to vendors and to users – is much greater.

What’s driving the current industry attention to valuations quality?

Two things. First, regulatory and audit oversight of valuation sources and processes has increased markedly since the financial crisis. The G20 placed valuation – in the sense of the essential need to know the true value of assets – at the centre of the turmoil, and initiated a programme to ensure that the issues highlighted by the collapse or bail-out of financial institutions were addressed. The way financial firms value their asset holdings has come under unprecedented scrutiny. Second, those institutions have themselves learned many lessons from the crisis and are determined not to have their fingers burned again!

Which markets and classes are best served by current industry offerings? Which are worst served?

For regular corporate and sovereign fixed-income securities, there are a number of well developed evaluation services, driven by the data strengths of the main data vendors, which have accepted methods and a good track record. There are fewer participants in the markets for mortgage products, and there is certainly more to take into account here from a data management and model calibration perspective. But the vendors in this space also have proven services.

Stepping outside of the fixed-income space, OTC derivative and structured product evaluations have more recent provenance.  There are some newer vendors, as well as smaller niche providers, involved in this segment, but Big Data has yet to come up with a truly comprehensive response here.  The specialist nature of the methodology and data, as well as the sometimes highly subjective calibration and input assumptions, make the evaluation of these asset classes a more uncertain business. OTC structured retail products, in particular, do not yet have a robust source.

When assessing third-party valuations services, what are the key parameters financial institutions should assess?

There are the usual questions relating to independence, reliability, consistency, etc. (and from a user perspective, cost is a much more important factor than many like to admit!). But we believe that in today’s world, the most important factor to judge is the defensibility of evaluations. The fundamental question a user needs to ask is: ‘Can I defend the use of this evaluation to anyone who may ask?’

To SIX Financial Information, ensuring defensibility means two things. First, the user must fully understand how the evaluation was produced. This implies that the full details of the methodology, data inputs and assumptions need to be provided to the user – full transparency. A user should never have to ask ‘how’ an evaluation was generated. 

Second, the user must be able to justify the use of the evaluation to any external party – client, regulator, auditor, risk group, etc. Having all of the necessary information to understand the evaluation is part of this. But so is having the comfort and assurance that there has been some kind of review and oversight of the vendor models and process.

In the case of SIX Financial Information, we felt that it was appropriate to have our Evaluated Pricing Service reviewed and assured by a major international audit firm, and their report on our service is available to our clients.

How important is transparency of methodology, both for suppliers of valuations data and for consuming organisations, who need to assure their own clients of the robustness of their models?

We believe that this is fundamental to the acceptance of an evaluated price; not only transparency of methodology, but its suitability for the job (preferably judged by a source independent of the vendor) and also the data inputs and assumptions that drove the model, operational process and controls. The age of the black box is dead! Above all else, the user needs to trust the robustness of the service and be comfortable recommending it to their clients.

Another factor here is the delivery of transparency not only to the users, but also to their end-clients. Connecting the vendor, the user and the end-client with the same amount of information greatly improves the quality and timeliness of resolving any queries or price challenges.

What about timeliness? Are we heading toward real (or near real)-time valuations pricing?

Given that the asset classes that lend themselves to evaluated prices are, except in some limited areas such as on-the-run US Treasury benchmarks, not real-time tick-by-tick markets, the notion of a real-time evaluation seems a little unusual. There are some services promoting this concept, but it is still new and remains to be seen whether it will develop into the orthodoxy.

Having said that, it is clear that many users now require multiple snap times and this trend is accelerating. The availability of this for all asset classes, however, is patchy. For some complex markets and OTC derivatives, an overnight batch valuations service, which allows the collection of all the required market data prior to evaluations, remains the norm. It is possible that this might improve with increasing access to liquid market data when some of this trading moves on-exchange.

Is there cross-over between valuations services designed for front office applications like trading and those geared toward portfolio valuations in the middle/back office?

This is the Holy Grail: front to back consistency on valuation. But it is surprisingly difficult to achieve in practice.

The whole approach to valuation differs in the front and back offices. In the front office, valuation tends to be forward looking – a trader or a fund manager will have a view, and possibly a position, in a specific instrument and, within reasonable limits, their assessment of the value will be informed by this view.

In the back office, and for vendors who service this market, the approach to valuation is essentially backward looking. A value is produced that reflects all the known market information relevant to this instrument at the time of the valuation. There is no attempt to second-guess this information or to tweak it to reflect a proprietary market or security-specific viewpoint. It would certainly be useful – and arguably sound practice – if the prices used in the front and back office were broadly aligned, but there are no guarantees.

What will be the next major developments in the valuations business?

We have already mentioned defensibility, which we believe will be the major driver for evaluations over the next few years. Increasing frequency of snap times and further expansion of coverage into previously poorly served areas are also likely.

One of the more interesting developments, though, relates to the requirement that many hitherto OTC-traded derivatives be exchange-traded and/or centrally cleared. This raises the prospect that much more market data on these rather opaque markets will become publicly available and consequently available for use in the evaluation process. One can expect that this will greatly improve the process for valuation of these asset types, but could it also be the spark for Big Data finally to get seriously involved in this segment?


Datawatch Announces Agreement To Acquire Panopticon To Deliver Real-time Big Data Visual Discovery Solutions

Information contained on this page is provided by an independent third-party content provider. WorldNow and this Station make no warranties or representations in connection therewith. If you have any questions or comments about this page please contact CHELMSFORD, Mass.

via Pocket June 17, 2013 at 04:12PM


NASDAQ OMX Launches WorkSpace Nasdaq : NDAQ

NEW YORK, May 6, 2013 (GLOBE NEWSWIRE) — The NASDAQ OMX Group, Inc. (Nasdaq:NDAQ) today announced the launch of WorkSpace, a new cloud computing platform that will expand the company’s Corporate Solutions client base and enter the burgeoning virtual data room (VDR) market.

via Pocket May 07, 2013 at 06:49PM

FlexTrade leverages OneTick to add enhanced analytics to EMS Platform–platform

First Published Monday, 15th April 2013 from Automated Trader : Automated Trading News

Offers integration of OneTick’s capabilities with FlexTRADER’s strategy servers, advanced analytics and signal generation

New York – OneMarketData has announced that FlexTrade Systems offers integration with OneTick, a single solution for complex event processing and historical and real-time tick data, to enhance FlexTRADER, its execution management system. By incorporating OneTick’s analytics capabilities into its EMS, FlexTrade users can employ a single platform to provide market insight.

OneTick’s CEP capabilities enable FlexTrade users to generate trade signals and develop strategies based on real-time and historical data. FlexTRADER will also tap OneTick’s historical database to store tick data as well as trade data for real-time and post trade analysis across asset classes, including equities, foreign exchange and listed derivatives.

“FlexTrade is committed to continuously evolving our platform to meet the growing needs of our clients,” said Vijay Kedia, President & CEO, FlexTrade. “OneTick empowers FlexTrades’s clients with powerful, proven analytics to efficiently and effectively create, test and implement quantitative strategies from one central platform.”

“Financial firms today are under increased pressure to develop and execute sophisticated quantitative trading strategies that can quickly discover untapped alpha in these volatile market conditions,” said Richard Chmiel, senior vice president at OneMarketData. “OneTick’s unique ability to draw on both real-time and historical data will give FlexTRADER users the advanced analytics they need to generate the superior trade alerts and signals they need to keep them ahead of the competition.”

Richard Chmiel, senior vice president, OneMarketData

Richard Chmiel, senior vice president, OneMarketData

“OneTick’s unique ability to draw on both real-time and historical data will give FlexTRADER users the advanced analytics they need to generate the superior trade alerts and signals they need.”

Swaps watchdog drowning in new data, regulator says (from Reuters)


By Douwe Miedema

WASHINGTON | Tue Mar 19, 2013 12:16pm EDT

WASHINGTON (Reuters) – A surge of new trading data is overwhelming the top U.S. derivatives watchdog, a senior regulator said on Tuesday, crashing its computers and barring it from effectively overseeing the market.

The flood of data on swaps – financial instruments used for speculation or to protect against risk – started coming in at the beginning of the year because of the Commodity Futures Trading Commission’s own new rules.

“The Commission now receives data on thousands of swaps each day. So far, however, none of our computer programs load this data without crashing,” CFTC Commissioner Scott O’Malia, a Republican, said in a speech.

The $650 trillion swaps market was largely unregulated before the 2007-09 credit meltdown, but global regulators have since started cracking down on the industry, which is dominated by the largest investment banks.

Swap deals used to be clinched bilaterally between market parties, but under the new regime, clearing houses will need to stand in between buyers and sellers, to reduce the risk that a failed deal causes a market rout.

The banks are now also sending data of each trade they do among themselves to data warehouses called Swap Data Repositories (SDR). But O’Malia said a lack of standards made it virtually impossible to use the data.

“This has become a serious problem. As it turned out, each reporting party has its own internal nomenclature that is used to compile its swap data,” O’Malia said.

The problem was so bad, that the CFTC was currently unable to find JPMorgan’s $6.2 billion loss on disastrous credit default swap trades last year, which became known as the “London whale” in the data, O’Malia said.

The CFTC had failed to specify the data format that swap dealers must use when sending their swaps to the data warehouses as it rushed through, O’Malia said, and there was also a lack of IT capabilities at the agency.

The data come in to the CFTC through the Depository Trust and Clearing Corporation, which performs back-office activities for investment banks, and runs an SDR which holds crucial data of swap deals between banks.

(Reporting by Douwe Miedema; Editing by Kenneth Barry)

Big Data, Magical Thinking and Investment Management

All information technology essentially offers an abstraction from an underlying reality, enabling that reality to be understood in simpler, more human centric and hopefully better ways.

via Pocket March 14, 2013 at 09:29PM

OTC Clearing and Regulations

My views on OTCs and Regulations

Knowledge Problem

Commentary on Economics, Information and Human Action


4 out of 5 dentists recommend this site

Aditya Ladia's Blog

Forex, Investment and Finance

Soltis Consulting, Inc.

Business Concepts, Ideas, and Information


An Endeavor To Explore The Uncertanity

All About Cyber Security and Financial Technology and Beyond

The Future of FinTech and Cybersecurity are Interlocked: Creating the Secure Future of Financial Technology Today


Read about latest trends in Algo Trading in India or visit our website

Trading Smarter

Thought Leadership, Insight and Product Information from TradingScreen

Tales from a Trading Desk

Noise from an Investment Bank

NPA Computers

Bringing you info about the latest on Internet Technology


An online journal of International Energy Trends, Green Building, Sustainability and Climate, A&E, Data, Security, CryptoCurrency and Social Media

Trade News in Brief

International Economic Affairs & Relations / Regional & International Organizations / Global Commerce & Business


The Single Dealer Platform Community

Carl A R Weir's Blog

A Cross Asset Connectivity and Finance site

%d bloggers like this: