Welcome to NexusFi: the best trading community on the planet, with over 150,000 members Sign Up Now for Free
Genuine reviews from real traders, not fake reviews from stealth vendors
Quality education from leading professional traders
We are a friendly, helpful, and positive community
We do not tolerate rude behavior, trolling, or vendors advertising in posts
We are here to help, just let us know what you need
You'll need to register in order to view the content of the threads and start contributing to our community. It's free for basic access, or support us by becoming an Elite Member -- see if you qualify for a discount below.
-- Big Mike, Site Administrator
(If you already have an account, login at the top of the page)
So essentially, they're using market sentiment, with intermarket analysis, to make money. Also, they're making swing trades, no day trades.
I really don't think theres anything new about this..... Alot of poeple trade the market like this, they're just using twitter. Also, it would have been more impressive if they made day trades. Much harder, much more crowded.
isn't there a flaw in an algorithm that follows crowd psychology?
If there is "force" in a twit or a million of them to make markets move, does this also assume that people who twit make a trade out of it? that would be a wrong assumption.
Also, twits get copied and retwitted as one's own with a slight change...this is one flaw that twitter has, the spam is out of control and it's not easily detectable. This could be picked up by an algo as a sentiment.
This is one complex Algo....all i know is this, simplicity still rules. The Ark was built by amateurs, the Titanic by professionals.
Trading futures and options involves substantial risk of loss and is not suitable for all investors. Past performance is not necessarily indicative of future results. You may lose more than your initial investment. All posts are opinions and do not claim to be facts. Please conduct your own due diligence. Use only Risk capital when trading Futures.
1 800 771 6748 local 561 367 8686 email [email protected]
Is there a flaw in an algorithm that follows the crowds? Maybe...maybe not.
Is there a flaw in an algorithm that claims a success rate of 87.6% accuracy? Maybe...maybe not.
My understanding of the original Bollen et al research is that they take the 'mood' if the twitterverse today using only those tweets with 'mood words' (e.g., tweets including "I'm feeling", "I'm", "I don't", etc). That mood is then used to predict the movement of the Dow Jones Industrial Average for tomorrow and a position is taken to take advantage of that prediction (long, short, etc).
In the original paper that the fund is based on, there are a few different accuracy rates with the 87.6% rate being the one touted by many people and the lower rates being ignored. That's interesting to me...why only focus on the best rate? The actual prediction methods aren't fully disclosed in the paper so I'm leery of the accuracy rates since there doesn't appear to be any method to easily reproduce the research.
My research is focused on seeing what value is actually in a 'tweet' and whether 'tweets' actually provide an predictive capabilities. My research is closer to the Sprenger & Welpe research and previous research performed using Yahoo finance message boards to determine whether message volume has any correlation with stock volume (some research says yes, some says not).
Is using the wisdom of the 'crowd' a valid approach to investing/trading? I think that traders that follow a momentum trading approach would as yes....when a lot of volume moves into a stock and price begins to go up (or down), many traders jump on board to catch the momentum train (i.e., the crowd is jumping on board).
Does an investing/trading approach using twitter as a decision making tool make sense? Don't know....but I will tell you that studying this approach is a valid way to finish my dissertation.