I covered this a few months ago when it was announced and now it appears they are almost ready to open for business. This is all mathematics with analytics to make this work and to be able to scour the web and Twitter to get the raw data and what filters they use is interesting. It’s all algorithms and their interpretations and in this case, heavy on the interpretations. In healthcare with data bases there’s a big on going project to match free text with tables, in other words what does that “really mean” and this is along the same line.
For example, Dr. Halamka at Harvard gave the perfect example of getting the right interpretation with stating the text says the man uses alcohol every day. Ok does this mean he’s a drunk and needs rehabilitation? That will be one of the possible interpretations. When we look further, the man is a diabetic and uses alcohol every day to clean his skin before an injection, so see how this works and we have the same types of issues here I would think. You can watch the video below for a little more history.
Also as a note there all kinds of healthcare companies wanting to find that perfect algorithm that can predict what patients will be readmitted to hospitals too. One group in California is offering a $3 million dollar bounty for those algorithms. Now if you want to graduate from Twitter algorithms to the heavy duty stuff that the CIA and other hedge funds use, take a look at the Business Insider here and see what Palantir Technologies does, no comparison. It’s a good read and even if you are not in investing, good to know what’s out there. BD
Six months, numerous inquiries, and one Caribbean brainstorming session later, Bollen is a consultant to a soon-to-be-opened U.K. hedge fund betting that 25 million sterling and one killer app will be enough to generate double-digit investment returns.
The fund, Derwent Capital, is scheduled to open for trading in early April. Run by a young entrepreneur with a background in foreign-exchange trading, the fund will use quantitative models to comb through millions of daily tweets and look for sentiment threads that could prove leading indicators of how stocks trade several days later.