The fact is anyone can *Predict the price of bitcoin, but will you actually put your own money to trade?
Like what we did here, http://financeai.com/forex/btc it does show some degree of correlation between sentiment and the price.
MIT computer scientists can predict the price of Bitcoin
61–70 of 86 posts
Re: MIT computer scientists can predict the price of Bitcoin
#62This is short-term trading. "Every two seconds they predicted the average price movement (on OKcoin) over the following 10 seconds. If the price movement was higher than a certain threshold, they bought a Bitcoin; if it was lower than the opposite threshold, they sold one; and if it was in-between, they did nothing." I don't see them allowing for commissions and fees. OKcoin, at peak, had a trading volume so high tha…
This is how I trade currencies, usually a Yen pair on a 30min timeframe. It does work and money can be made, but it is a lot less profitable then they claim (on the Yen pairs I trade). Generally, a very outsized event can erase quite a lot of gains. Even smaller ones can make you give back a bit (such as NY ebola news or surprise BoJ news). Over time those commissions/fees add up. Still, over time I would bet they could be profitable on this strategy on some timeframe. Of course, just profitability is a very different claim than their own.
Re: MIT computer scientists can predict the price of Bitcoin
#6389% over 2 months. Not bad. My algorithm did 8,000% over 6 months using real money on real exchanges and I have the trade history to back it up.
Re: MIT computer scientists can predict the price of Bitcoin
#64The paper states that the strategy was simulated with live data and makes no mention of slippage. I've never traded bitcoin so I'm not sure how difficult it is to get fills, but that along with spreads are non-trivial components of real trading.
it would have been better if they set up an wallet and put bitcoin in it and demonstrated the trades that were automatically executed by this wallet. Since bitcoin is a ledger history, we could be 100% certain that SOME algorithm 'did the right thing', although we couldn't be certain that they spun up more than one algorithm and then just showed us the best one.
Trading doesn't happen on the blockchain, it's far too slow.
Re: MIT computer scientists can predict the price of Bitcoin
#65The problem with the paper is not overfit. They claim to have run their simulation with out of band ("live") data. The actual problem with the paper is that we have no idea if their simulator is any good, which means that their result (89% return in 50 days) could be totally bogus. In other words, we don't know if the actual bitcoin exchange would fill their orders at the same prices (if at all) as their simulator do…
People so often overlook the role that execution plays in trading. As time scales shrink the impact of execution increases, and indeed many HFT strategies are not profitable without top tier execution (both in terms of fee schedules and technology). This is also one of the places that most academics fail when analysing a trading strategy. They make typical "assume a frictionless surface" types of assumptions that bre…
I see no mention of the spread, costs or even ability to put on a short position, exchange lag variability (huge issue when simulating even on modern exchanges, let alone fly-by-night bitcoin markets). Additionally, it is very easy to find trend-following signals that "work" but break down when conditions change very quickly. That seems to make up most of the prediction, along with an order book imbalance signal that might be more stable.
I think a better approach would be looking at order book features and lags vs. other markets. The costs are high on BTC markets so it would be pretty tough to overcome those though. Anyone with experience to do this is probably doing it somewhere more lucrative. I think BTC markets only trade a few million USD a day.
Re: MIT computer scientists can predict the price of Bitcoin
#66Earlier quoted context omitted.
> What this group at MIT may have done is reverse-engineered the fake trade generation algorithm. Just to be clear, there is nothing wrong with this. Infact, sitting around and reverse engineering what other traders are doing is what many funds do. I'm in this group so I"m happy to answer questions if anyone has any. > Every two seconds they predicted the average price movement (on OKcoin) over the following 10 secon…
Where can I read about the actual strategies used? Perhaps some that aren't used any more. I've read an absolute ton about how to set up a trading system with hadoop and cassandra and blah blah but that's all pretty trivial. I'd be more interested in the strategies... this decay factor is interesting. Where did you find out about this?
A simple signal would be more shares bid than offered at the inside market. Imagine a market with 1000000 shares bid at $4 and 100 shares offered at $4.01, it's more likely to tick up than down in the very near-term. This isn't tradable though since the predictions aren't large enough to overcome the spread and you can't expect to join the 1000000 share bid and trade when it's good (the 1000000 shares that made you think it was going to move up all have to trade or cancel for you to trade, not looking so great anymore).
Real HFTs use other features of the order book, movements in related products (maybe a move in oil futures in the last minute impacts the price of an airline stock in the next 10 seconds, etc.), and so on. The signals are not really that complicated, but competitors eventually converge on knowing the same signals and compete them out of existence/profitability. Also, how you execute around your prediction matters just as much if not more.
http://queue.acm.org/detail.cfm?id=2534976 and http://queue.acm.org/detail.cfm?id=2536492 have some more examples. http://www.decal.org/file/2945 also has some ideas for old signals that probably won't work anymore.
Re: MIT computer scientists can predict the price of Bitcoin
#67Earlier quoted context omitted.
>Any marketplace is 'zero sum' if you think about it. vs >I'm not arguing that it is zero-sum So, what are you saying there then.
How can the stock market be zero sum. What about dividends?
Zero sum markets are not really a thing. The normal phrase is 'zero sum game'. Buying and holding stocks is not a zero sum game - you make money. Trading stocks between speculators where the trading commissions exceed the dividends and long term market appreciation is a zero sum game. Same market, different games.
Re: MIT computer scientists can predict the price of Bitcoin
#6889% over 2 months. Not bad. My algorithm did 8,000% over 6 months using real money on real exchanges and I have the trade history to back it up.
Jordan Belfort, is that you?
Re: MIT computer scientists can predict the price of Bitcoin
#69By publishing the paper you essentially invalidate it, as people take advantage of it. Happens time and time again in any market.
Re: MIT computer scientists can predict the price of Bitcoin
#70Earlier quoted context omitted.
People so often overlook the role that execution plays in trading. As time scales shrink the impact of execution increases, and indeed many HFT strategies are not profitable without top tier execution (both in terms of fee schedules and technology). This is also one of the places that most academics fail when analysing a trading strategy. They make typical "assume a frictionless surface" types of assumptions that bre…
I see no mention of the spread, costs or even ability to put on a short position, exchange lag variability (huge issue when simulating even on modern exchanges, let alone fly-by-night bitcoin markets). Additionally, it is very easy to find trend-following signals that "work" but break down when conditions change very quickly. That seems to make up most of the prediction, along with an order book imbalance signal that…
About 35 million USD in trades on the public bitcoin-paired markets today. About 40 million USD today in total volume for all pairs on these exchanges.