Unsupervised machine learning with basket clusters
hackernoon.com
hackernoon.com
He has a dataset that links companies to each element of the periodic table (Intel would likely be highly linked to silicon, while not as linked to nitrogen as a fertilizer company). He then uses some clustering and whatnot to produce groups of stocks he is trading as a unit.
How he picks what to trade is kinda hand wavy (Is he trading all baskets and only reporting the good one?). He also mentions using Google trends data, which might be some signal for his clusters. Given the lack of detail, my gut reaction is to assume he made tens of these strategies and has kindly reported the best one to us.
At the end, you see he is a financial consultant hoping to build his resume up through posts like these.
This seems like a classic example of hindsight. There are many things one can tell on hindsight when the results are out. The key is if they will hold for the future too. Am I missing something?
Does that help?
I don't have to "back up my claim" the math does it for me already! You're asking me to prove a negative--instead, show me one example of a firm that has beaten the market without resorting to funny business and I'm all ears.
Consistently beating the market would indeed be an extraordinary claim, because we havent seen that a lot (if at all).
Also -- if I were a quant that managed to beat the market consistently, I would shut up and go straight to RT, for two reasons. To avoid toxic dubious comments like yours, and because RT can pay me better than your standard hedge fund.
http://www.reuters.com/article/simons-hedge-idUSN21355752200...
The challenge is that those patterns appear and then they disappear mostly forever because they are frequently created by someone else's mistakes like Nassim Taleb buying way out of the money put options that never really created any significant profit. Free Alpha, get your free Alpha, right there.
To tap into those patterns while they are profitable, you need a lot of smart people, and a great deal of infrastructure for experimentation and delivery of strategies that can tap into those patterns before they disappear. While you're right that it is possible that they cheat, it's also possible that they have a sufficiently sophisticated infrastructure to actually make this work. It's kind of like how Nintendo only ships 1 out of 3 video games they develop. All IMO of course.
His other point about the rarity of regularly beating the market certainly supports some amount of skepticism of RT, in my view. It's extraordinary, and it's an extraordinary claim that suddenly the particular talent at computational trading at RT is better than the legion of super genius other quants and techies who have been doing this for years.
Disclaimer: I haven't a dog in the fight with respect to supporting or taking RT down. As I see it, being a small time player, my trading strategies are necessarily constrained to the point where RT's methods, legit or not, aren't applicable. So whether they win or lose doesn't make a difference to me.
http://www.reuters.com/article/usa-irs-hedgefunds-idUSL3N0ZP...
"The dataset is based on relationships between elements in the periodic table and public companies."
This description is a bit vague.
Beat the market by 10% with k-means clustering and a feature set derived from companies and chemical elements! Hahahaha no.
Is there a danger than whatever gains you were able to capture with a unique insight will end up being shared with competitors?
On the other hand when he starts selling and others sell as well speed is a critical factor as the downward pressure will make the later movers the biggest losers.
To anyone who takes this seriously: I have a price of butter in Bangladesh indicator which works REALLY WELL on the S&P500.