Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MIT computer scientists can predict the price of Bitcoin

newsoffice.mit.edu

Post reply on HN
Print view View original

31–40 of 86 posts

Re: MIT computer scientists can predict the price of Bitcoin

#31

Post by latj »

minimax wrote: post #29

The 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…

Imagine if someone learned how to legally print money and their first action was to tell the world-- then I would be extremely skeptical.

Re: MIT computer scientists can predict the price of Bitcoin

#32

Post by foobarqux »

chollida1 wrote: post #14
Animats wrote: post #10

This 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…

> 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…

> 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.

His point is that the posted trades were not in fact tradeable.

Re: MIT computer scientists can predict the price of Bitcoin

#33

Post by foobarqux »

barisser wrote: post #4

This seems like massive historical overfit, which can lead to arbitrarily precise fit, but no predictive capability. Any model, if given enough parameters, can be made to match historical data to an arbitrary degree. I also run several Bitcoin bots. I can tell you that slippage is not insignificant. If you make transactions every ~10 seconds and incur 0.1% fees each time, this is an extremely significant effect in ag…

Curious as to your returns, how they have changed over time and if you are doing this full time.

Re: MIT computer scientists can predict the price of Bitcoin

#34

Post by panarky »

lrm242 wrote: post #26
panarky wrote: post #24

Earlier quoted context omitted.

Most marketplaces are not zero-sum. For example, futures and options are zero-sum because every dollar of profit that one trader makes is offset by a dollar of loss from another trader. But stock markets are not zero-sum. Prices can be bid up without a single share changing hands, creating new wealth out of thin air, and everyone wins. Conversely, prices can go to zero, destroying wealth and making everyone a loser.…

You're mixing the concepts of realized and un-realized profit. A market price change marks your open position and gives you an unrealized (loss)gain. But to realize that you have to trade, plain and simple. And someone must take the other side of that. A more compelling argument against zero-sum is that traders and investors have different time frames and objectives. And, indeed, the classic argument in the futures m…

I start a company to make cheap autonomous flying cars. I invest $1,000 of my own money and build a working prototype. It looks promising, so you buy 50% of my shares for $10,000.

I just made a 20x return on my investment, and you own 50% of a great opportunity. Who's the loser here that makes this a zero-sum market?

Our autonomous flying cars go into production, and now your 50% is worth $100 billion, and you sell your shares to Elon Musk. Where's the zero sum?

Re: MIT computer scientists can predict the price of Bitcoin

#36

Post by rwissmann »

Animats wrote: post #10

This 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…

Plus, from a quick glance, it looks like in-sample data with optimisation of parameters around scaling and holding periods.

Fee-less trading on in-sample data. You can get the same return on futures markets with that.

Re: MIT computer scientists can predict the price of Bitcoin

#37

Post by dash2 »

sillysaurus3 wrote: post #11

I fixed the article's headline image: http://i.imgur.com/QVgcgNI.png If everyone began using the paper's strategy, would the strategy still work? Also, the strategy seems less effective than portrayed in the news article. If you look at the "results" section, it seems like the profit flatlined shortly after starting, then had success due to some major trading event, then eventually flatlined again: http://i.imgur.com…

I think equation 4 is just derived from equation 3. The top bit counts every time before that y_i has taken a particular value y, and multiplies it by the distance of the x value then, x_i, from the value of x now. (Squared and exponentiated because this is the pdf of the normal distribution.)

Here's an interpretation: if there were no noise, you might just count the number of times x took on a particular value and y took on a particular value, and divide that by the total number of times x took on that value. This would give you an empirical estimate of the prob of y given x.

Because there's noise, they weight the counts by the pdf of the normal distribution of x - x_i. So, whenever x_i was close to current x, and y_i was a given y, that increases the probability of y occuring now.

Re: MIT computer scientists can predict the price of Bitcoin

#38

Post by lrm242 »

panarky wrote: post #34
lrm242 wrote: post #26

Earlier quoted context omitted.

You're mixing the concepts of realized and un-realized profit. A market price change marks your open position and gives you an unrealized (loss)gain. But to realize that you have to trade, plain and simple. And someone must take the other side of that. A more compelling argument against zero-sum is that traders and investors have different time frames and objectives. And, indeed, the classic argument in the futures m…

I start a company to make cheap autonomous flying cars. I invest $1,000 of my own money and build a working prototype. It looks promising, so you buy 50% of my shares for $10,000. I just made a 20x return on my investment, and you own 50% of a great opportunity. Who's the loser here that makes this a zero-sum market? Our autonomous flying cars go into production, and now your 50% is worth $100 billion, and you sell y…

First, I never claimed the markets were or were not zero-sum, only that your attempt to explain was wrong as it mixed realized and unrealized profit.

Second, zero sum requires a definition of utility for each participant. If those definitions vary (and they almost assuredly do) then a reasonable argument can be made that to define whether the activity is a zero-sum game or not requires a commonality amongst those utilities (dollars, for example). This is often not the case in trading (for example, the farmer hedging his crop with a speculator who seems to profit short term).

Re: MIT computer scientists can predict the price of Bitcoin

#39

Post by lrm242 »

minimax wrote: post #29

The 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 break down in a real market.

To your point, high-frequency simulation is damn hard and it is highly likely that they failed here and have tainted their results with bad simulations. Most of these papers would be well served to avoid dollars and cents and simply analyse the statistical qualities of their signal to their target over time. That is the first step in this business, anyway. Simulations only happen once the signal has been through the wringer.

Re: MIT computer scientists can predict the price of Bitcoin

#40

Post by Enzolangellotti »

barisser wrote: post #27
vmarsy wrote: post #21

Earlier quoted context omitted.

In red is your model whereas in green is the real one, M being the number of parameters. The technical term for the last one is "overfitting" if I remember correctly. But in the case you have an enormous amount of data, it is unlikely to happen. It reminds me of this awesome course: https://www.coursera.org/course/ml edit: The parent's parent's parent mention overfit for the MIT work, I don't think it'd be the case i…

Here's another way to think of it. If the parameter space for my model includes, let's say 10 binary decisions (which is very conservative), that's 1024 possible states of my model. If I tested all 1024 states against historical data, it is likely that some of them might do very well (depending on the general architecture of the model of course). What if I then selected the successful minority and held them up as cle…

There is a fun chapter on this topic in Jordan Ellenberg's latest book "How not to be wrong". It's called the "Baltimore stockbroker fraud".
Post reply on HN