
The new Wall Street Birds real-time Social Media Trading Software analyzes thousands of social media messages every second, compiling data that you can use for research, system development and real-time stock, futures and forex signal creation.
As described in the Wall Street Birds overview video and F.A.Q.s, scientists recently published a white paper titled "Twitter mood predicts the stock market". Johan Bollen; Huina Mao; Xiao-Jun Zeng (2010), Journal of Computational Science 2: 1–8.
This scientific study validated what our sister company Modulus Financial Engineering Inc., has been doing since 2004. The relatively recent popularization of social media has allowed us to greatly improve our systems and now we are offering our Social Media Trading Software to the public.
Key Features










*The historic data DVD, available for a limited time only, is invaluable for trading system development. Historic data may be updated via the optional real-time data API or CSV data files.
Wall Street Birds GPGPU-based servers use a patent-pending A.I. system to extract emotions from social media messages in real-time, in ten languages including English, Chinese (Mandarin), Spanish, Arabic, Hindi, Bengali, Portuguese, Russian, Japanese and German.
This data is extremely sensitive to world mood and economic conditions. Typically the data is highly correlated with price movement, even on a one-minute bar level. Researchers have claimed that our data can predict the VIX by up to six days.
Can social media really predict the stock market?
Scientists published a white paper titled "Twitter mood predicts the stock market" in October of 2010. They found that Twitter mood predicts the stock market with correct results 87.6% of the time, several days in advance. Johan Bollen; Huina Mao; Xiao-Jun Zeng (2010). "Twitter mood predicts the stock market". Journal of Computational Science 2: 1–8.
We have found that our data is also correlated with futures and forex data.
How are emotions defined?
Wall Street Birds servers use a patent-pending artificial intelligence system to extract emotions from social media messages in ten languages including English, Chinese (Mandarin), Spanish, Arabic, Hindi, Bengali, Portuguese, Russian, Japanese and German.
The emotion definitions are based partially on the work of Professor W. Gerrod Parrott.
Parrott, W. G. (Ed.). (2001). Emotions in Social Psychology. Philadelphia: Psychology Press

Our NLP engine is the most advanced of it's kind. In fact, we bet there will never be another NLP engine as advanced. With two years in the making our NLP engine uses several forms of artificial intelligence to process messages and identify their true meanings, in ten different languages. The sample below makes it very clear that we are doing something extremely advanced. Only a human reader could interpret the meanings of these messages with such accuracy while standard LSI systems would fail miserably...

This sample makes it very clear that we are not simply searching for keywords within messages. We go far beyond latent semantic indexing and Bayesian statistics. Our system is aware of word-use patterns over time.
In fact we have compared our NLP engine with those in the various whitepapers and it was clear that our engine beats the others hands down.
Perhaps our NLP engine is more accurate than the reported 87.6% rate at predicting the markets. That's to be determined.
But what we can say for certain, is that our engine can't be made better. If you're looking for the best of the best, this is it.
Note that this software is also available for white label use to
brokerages and proprietary trading firms.
Contact
sales@wallstreetbirds.com
for details.
Even though Social Media based Trading Systems are based on scientific evidence, we must still list the standard CFTC and SEC disclaimers for legal purposes:
Commodity Futures Trading Commission Disclaimer
Hypothetical performance results have many inherent limitations, some of which are described below. No representation is being made that any account will or is likely to achieve profits or losses. No hypothetical performance results are shown because in fact, there are frequently sharp differences between hypothetical performance results and the actual results subsequently achieved by any particular trading program. One of the limitations of hypothetical performance results is that they are generally prepared with the benefit of hindsight. In addition, hypothetical trading does not involve financial risk, and no hypothetical trading record can completely account for the impact of financial risk in actual trading, for example, the ability to withstand losses or to adhere to a particular trading program in spite of trading losses are material points which can also adversely affect actual trading results. There are numerous other factors related to the markets in general or to the implementation of any specific trading program which cannot be fully accounted for in the preparation of hypothetical performance results and all of which can adversely affect actual trading results. It is important to understand that "day trading" is not considered investing, rather it is speculating. As with any form of speculation, there are significant risks. Day trading is fast paced and may lead to large financial losses.
SEC Disclosure
Modulus does not promote stocks in the Service or on the web site. Modulus does not receive any compensation from companies whose stocks appear in the Service or on the web site and Modulus has no financial interest in the outcome of any stock trades mentioned therein.