Gautham Sastri will be speaking at Newsweek’s Artificial Intelligence & Data Science in Capital Markets Workshop

Screen Shot 2017-11-02 at 9.31.07 AM

iSentium CEO Gautham Sastri will be on the NLP panel. Mr. Sastri has co-authored patents both in cloud storage and sentiment extraction.

Details for the workshop info can be found here.

GS portrait
Gautham Sastri

Info on Mr. Sastri’s appearance can be found here.

About iSentium

Founded in 2008, iSentium uses patented Natural Language Processing (NLP) to extract sentiment from unstructured social content then instantly transforms it into highly actionable indicators in Finance, Brand Management and Politics. iSentium is proven in the market and is vetted by J.P. Morgan and NASDAQ.

iSentium’s management team brings a wealth of experience from both industry and academia with skills ranging from Big Data, finance, linguistics and signal processing. Our world-class team comprised of linguists, quants and computer scientists has collectively published over 200 papers and 18 books.

Knowledge is power. Knowledge is alpha. Knowledge is edge. iSentiumKnows.™

To learn more about what iSentium can do for you, call Jake Sedlock, Chief Revenue Officer, at (206) 683-6003. Or send him an email at: Jake.Sedlock@iSentium.com

 

 

 

 

iSentium Uses AI for Sentiment Analysis of Social Media [Interview]

iSentium, which has offices in the US and Canada, harnesses applied artificial intelligence to extract sentiment from unstructured social media content and transform it into actionable insights in verticals such as finance, politics, and brand management.

Founded in 2008, iSentium’s expert team hails from both industry and academia and has collectively published more than 200 papers and 18 books.

Machine Intelligence iSentium: Breakthrough Sentiment Analysis

iSentium’ CEO, Gautham Sastri, talks about the inspiration behind the company, its patented NLP technology, the power of social media content, and more.

What’s your role and what does that entail on a daily basis?

I am the CEO of iSentium. Given the small size of our team, I am deeply involved in the day-to-day running of the firm.

I focus heavily on:

A) product development, leveraging my data science skills developed over a 30-year career in signal processing, seismic acoustics, and weather forecasting; and

B) sales and market development, given that we are in early innings with respect to applied artificial intelligence.

GS Screen

What did you do prior to joining iSentium?

I attended the University of Houston where I studied electrical engineering and history.

I started my career working for the US Navy writing signal processing algorithms to look for Russian submarines. Subsequently, I spent a few years at NEC in their supercomputing division before embarking on the entrepreneurial route.

My first startup, Maximum Throughput, supplied racks of servers to clients, including the Los Alamos Laboratory. While at Maximum Throughput, I was invited to join Intel’s Server Advisory Council, which was tasked with providing key inputs to their server technology roadmap.

Upon acquisition of Maximum Throughput by Avid Technology (Nasdaq: AVID), I started Terrascale, which provided cloud storage solutions (in 2003) for large scale text analysis.

Terrascale was acquired by Rackable (now SGI Corp). I became COO of the new entity and managed a $500M business.

What was the deciding factor that led you to join iSentium?

With the advent of social media, I saw an opportunity to commercialize text analysis for actionable insights across verticals and domains.

iSentium had a talented team of linguists led by Anna Maria Di Sciullo, a professor at the University of Quebec who had studied under Noam Chomsky at MIT.

I got involved initially as an investor and then joined the company as CEO in 2010.

What’s the most challenging aspect of your role?

Educating the market and proving the value of social media data has been a key challenge that we have slowly been overcoming.

The nature of social data is very different from traditional data sets and hence requires new methods of analysis.

That being said, we have done a fairly good job proving the value proposition in capital markets and trading, where you have a binary outcome.

What was the inspiration behind iSentium?

The big opportunity to analyze and interpret a galactic amount of social content was a prime consideration.

Relatively speaking, platforms’ (Google, Facebook) lack of focus on the content made this opportunity even more interesting and attractive.

Early focus and research under the leadership of one of the top linguistics experts provided the right platform to embark on our vision to “Decode Social Sentiment.”

How do you utilize big data and NLP to analyze sentiment in social media content?

We are connected to Twitter and have access to both historical and real-time social media content.

Our NLP technology can assign a sentiment score to each message in about four milliseconds and can scale horizontally to process millions of messages per second.

Machine Intelligence iSentium: How iSentium Works

To what verticals are you currently applying your technology?

Our three verticals are Financial Indicators, Political Insights, and Brand Analytics. Finance came first.

How has your focus shifted over time, if at all?

We are being approached about leveraging our NLP capabilities to extract consumer sentiment by leading advertising agencies, management consulting firms, and brands themselves.

Where do you see the biggest opportunity in the long run?

While we will continue to deepen our penetration in financial services, we believe the bigger opportunity is in consumer sentiment that applies across industries.

We have already proven our efficacy and ability to mine sentiment cross-vertical, having run multiple proof of concepts on consumer sentiment on fast food and restaurant chains.

Machine Intelligence iSentium: Brand Analytics

How would you define your key value proposition for customers?

We produce the most accurate interpretation of natural language given a particular context.

For example, in finance, we have reached an 80% accuracy rate where a human agrees with the machine in its understanding of a given piece of text related to the stock market.

How would you describe your typical customer?

Within financial services, our clients range from leading quantitative hedge funds and systematic global macro funds to high frequency trading firms and investment banks.

Our new product suite for financial services is a real-time dashboard that will enable asset managers and long/short hedge funds to quickly sift through social media data and develop insights for fundamental analysis.

Machine Intelligence iSentium: Financial Indicators

Was the product fully designed and developed in-house?

Our NLP capabilities have been built from the ground up since 2008. At any point, we have had up to six PhDs in linguistics working on the product.

We filed a family of patents in the early part of the decade and have already been granted two patents. We did not use any open source tools.

How much training data do you typically require for a new customer?

We don’t train our models, and there is no machine learning involved.

For stock sentiment, we have a lexicon of about 15,000 words that is used for analyzing text and assigning sentiment scores.

How quickly can your system react to news on social media and adapt your signals?

Depending on signal logic, we can react instantaneously to a burst of social chatter or it can be much slower moving and relies more on continuous sentiment extracted from a much longer time period.

Machine Intelligence iSentium: Politiical Insights

What’s the most exciting trend in machine learning from iSentium’s perspective?

In our view, machine learning does not simulate natural language learning by humans.

The universal properties of natural languages are not learned by humans who may make mistakes with vocabulary items, but not with the structure-dependent properties of natural language. 

Whatever language they are exposed to, humans (particularly children) are capable of inducing a grammar for that language without formal or algorithmic instructions.

In essence, humans are able to learn language deterministically. On the other hand, machine learning algorithms tend to learn from scratch and after extensive training periods.

What advances in machine learning have benefitted iSentium the most?

Instead of machine learning, iSentium relies on an innovative artificial intelligence structure-dependent technology.

This patented technology makes correct predictions on the sentiment of short texts, such as tweets, where natural language constituents are missing, as well as longer texts, which may include non-relevant topical information.

Both covert and irrelevant topical information cannot be dealt with by natural language technologies based on machine learning. For example, in the case of short messages, the covert information is not learnable because it is not explicitly included in the message.

Machine Intelligence iSentium: Quote from iSentium CEO

Are there any limitations on machine learning iSentium would like to see removed?

Machine learning is not a simulation of learning expressions in any natural language by human’s brains. It is a matter of modifying the algorithm’s parameters at each step to reduce the error value.

Neural networks are assumed to be non-deterministic algorithms. Non-determinism is one of the limitations of machine learning preventing it from simulating human intelligence.

This is particularly the case for machine learning based NLP applications, ranging from information retrieval to information extraction, including sentiment mining and question answering systems. 

The compelling evidence comes from recent discoveries related to the granular modularity of the human brain, which is the biological basis of the human capacity to express simple and complex thoughts using natural language.

Does iSentium consider itself a machine intelligence company?

iSentium is an artificial intelligence company that simulates natural language processing by humans.

Its universal core can be parameterized to any natural language, as well as to any domain of interpretation, including finance, politics, and brands. Effectively, it mimics human natural language intelligence.

We have packaged our underlying sentiment data through a few applications already, including finance, where we have built a significant presence and brand on Wall Street, and are now providing highly actionable solutions to advertising and other verticals.

About iSentium

Founded in 2008, iSentium uses patented Natural Language Processing (NLP) to extract sentiment from unstructured social content then instantly transforms it into highly actionable indicators in Finance, Brand Management and Politics. iSentium is proven in the market and is vetted by J.P. Morgan and NASDAQ.

iSentium’s management team brings a wealth of experience from both industry and academia with skills ranging from Big Data, finance, linguistics and signal processing. Our world-class team comprised of linguists, quants and computer scientists has collectively published over 200 papers and 18 books.

Knowledge is power. Knowledge is alpha. Knowledge is edge. iSentiumKnows.™

To learn more about what iSentium can do for you, call Jake Sedlock, Chief Revenue Officer, at (206) 683-6003. Or send him an email at: Jake.Sedlock@iSentium.com.

This article has been edited for length. Link to the Original content can be found here: http://thinkapps.com/blog/development/machine-intelligence-isentium-interview/

Nasdaq’s Machine Learning Hub Cuts Through Unstructured Data Noise Using iSentium Data

Turning Big Data into Small Data – Nasdaq, the world’s first electronic exchange, has ‘fintech’ running through its veins, and today introduces its latest innovation to support growing market demand for unstructured data sets.

The Nasdaq Analytics Hub will pull in data from Nasdaq’s own feeds as well as from a number of financial technology start-ups such as iSentium, which specializes in collecting and crystallizing massive unstructured social media content, into market intelligence; in other words, to turn Big Data into Small Data, and Small Data into trading and investment signals.

DATA

Four data sets are being introduced as the initial offering within the Hub. In addition to social conversations, it will take in central bank communications scored and profiled from the G-10, retail investor sentiment collected as investors make decisions to form strong short- and long-signals, and Nasdaq Dorsey Wright technical analysis that ranks securities, ETFs, and Mutual Funds based on relative strength.

The Analytics Hub is one of multiple initiatives coming out of Nasdaq’s Innovation Lab, a virtual workshop led by a select group of Nasdaq technologists and data scientists. The lab leverages cutting edge, scalable technology to provide Nasdaq’s clients with comprehensive multi-asset class market data solutions. Nasdaq Trading Insights was the first product to debut from the Innovation Lab last November.

New ways to find alpha-generating insights – Within the Analytics Hub, Nasdaq gathers normalized data from iSentium and other partners, before validating it and using machine intelligence to check that each data set possesses potential alpha-generating capabilities. Each data set is then thoroughly back-tested to ensure it stands up to rigorous testing in the field.

“We look at social sentiment data – that iSentium provides – as well as retail investor sentiment data and macro sentiment data. We also have our own proprietary technical analysis and machine learning-based events to draw upon. And, we are currently looking at a whole host of new data sets that we believe will be valuable to the marketplace,” says Terry Wade, senior vice president and head of business development and product, Global Information Services at Nasdaq.

He adds that further down the road, the Nasdaq Analytics Hub will have hundreds of data sets for clients to utilize:

“Our goal is to make it easier for the market (fund managers, active traders, quant funds etc.) to access valuable information in ways that would otherwise be difficult to do on their own.”

Social media sentiment from iSentium is one of the first four data sets available in the platform. Its team, which is led by Founder and CEO, Gautham Sastri, consists of linguists, quants and computer scientists whose primary mission is to find meaning or sentiment, in the terabytes of data that are produced on a daily basis.

Social data spans a wide spectrum. Facebook can be thought of as a cosy environment in which to share personal stories and events with one’s network, LinkedIn is the place for professionals to share business-to-business content, while Twitter is akin to someone shouting from the rooftops; a kaleidoscopic flow of 140-character data.

“When you arm millions of people with mobile devices and give them infinite bandwidth at low cost, they start messaging and tweeting, and it creates vast unstructured content. It represents the wisdom of the crowd, and is not machine-generated, so making the meaning obvious is valuable” says Sastri, who confirms that the Brexit decision started to become clear to his team some eight days before the final result was announced.

There is, says Wade, a desire to take people’s thoughts, emotions and actions and find signals and value in this vast unstructured content.

“The financial industry traditionally consumes oceans of high quality market data, so we thought, ‘How can we provide our clients with more of an edge in the market?’ How can we take it beyond what structured data offers and provide valuable information to people, to implement into their models and trading strategies?

“That’s what led to the development of the analytics hub,” explains Wade.

This underscores Nasdaq’s willingness to not only move in tandem with market evolutionary trends but to be at the vanguard of such trends, of which unstructured data consumption is just the latest example.

In Wade’s view, there will be increasing automation throughout the buy-side community, including increasing automation in research functions and trade selection. “To allow people to do that in an efficient way, we need to provide them with vast sets of accessible, cutting edge data,” he says.

Each of those data sets can then be confidently used and applied to clients’ trading strategies as a way to seek out new ideas and optimize entry and exit points.

Before determining whether to buy a specific stock, why not look at the market sentiment? If it looks favorable, it might be a good time to execute but if sentiment is trending down, maybe it would be best to hold off.

“One of the interesting things we’ve found is that while most people think of Twitter as a short-term signal, the bulk of work that both iSentium and Nasdaq have done, shows that these signals actually persist much longer than a minute or an hour,” reveals Wade.

Can you hear me…? While a stock exchange like Nasdaq generates very significant amounts of structured data per day, Twitter alone generates exponentially more: a terabyte of data every four seconds. People want to be heard in today’s world.

Still, that is a lot of noise to scan through and begin to make sense of.

“I don’t view stock market data as being competitive with what we do, which is to provide market intelligence. We are trying to add more color to the existing systems that deliver information, rather than replace them.

“The problem that we solve is the ability to process all this flow of social sentiment, which remember, doesn’t necessarily have to be rational,” says Sastri.

In effect, iSentium can best be thought of as a reporting business. It isn’t a quantitative business that provides people with a moneymaking solution, just as using a Nasdaq market data feed does not guarantee anyone will make money.

It all boils down to intelligence.

People use Nasdaq data feeds because they provide a reliable, accurate representation of the market at any given time.

“In our case, we look at a huge volume of social sentiment data, processing over 2000 messages per second with near zero latency to build patterns which show proven correlations to market performance. It’s an extraordinarily complex issue,” says Sastri.

Nasdaq receives iSentium’s processed data and then validates it. “We make sure the data is complete, we put it through our internal algorithms to back-test it using historical event data, and then we wrap it and send it to our clients. We do this for each and every data file we receive from our partners,” explains Wade.

The data–either raw or refined depending on the client’s preference—can be used across asset classes but it is mostly used for equities.

“Another of our partners, Prattle, mines central bank communications, and while this information is directly useful to many fixed income and global macro managers, we’ve taken that signal and shown clients how they might trade equities based on it as well,” confirms Wade.

The creation of the Nasdaq Analytics Hub to handle unstructured, non-traditional data sources shows just how fast the world is evolving. Sentiment data can reveal fear or optimism in the markets and, given it has been forensically analysed and processed, provide an important tool in refining one’s trading strategy.

Wade believes that people are going to want to consume ever more data to do their jobs better in a more automated way, “And we think we can extend our leadership position in the delivery of data to include this vast marketplace of unstructured, and unique, data..

“We’ve always been a strong technology company and we will continue to build on that heritage.

Link to original content can be found here:  http://business.nasdaq.com/marketinsite/2017/Nasdaqs-New-Machine-Learning-Hub-Cuts-Through-Unstructured-Data-Noise.html

About iSentium

Founded in 2008, iSentium uses patented Natural Language Processing (NLP) to extract sentiment from unstructured social content then instantly transforms it into highly actionable indicators in Finance, Brand Management and Politics. iSentium is proven in the market and is vetted by J.P. Morgan and NASDAQ.

iSentium’s management team brings a wealth of experience from both industry and academia with skills ranging from Big Data, finance, linguistics and signal processing. Our world-class team comprised of linguists, quants and computer scientists has collectively published over 200 papers and 18 books.

Knowledge is power. Knowledge is alpha. Knowledge is edge. iSentiumKnows.™

To learn more about what iSentium can do for you, call Jake Sedlock, Chief Revenue Officer, at (206) 683-6003. Or send him an email at: Jake.Sedlock@iSentium.com.