Bitcoin Forum

Economy => Speculation => Topic started by: K128kevin on March 21, 2014, 04:36:44 PM



Title: Prepare for 4am dip
Post by: K128kevin on March 21, 2014, 04:36:44 PM
Hey guys, so I have a slightly more reasonable prediction than the "prepare for march 16th dip" post made a little while back.

As some of you may have seen in a post I made several days ago, I have been working on software that uses neural networks to predict bitcoin prices. The predictions can be seen at http://www.btcpredictions.com/

The short term neural network has been consistently predicting a dip from around $585 down to about $562 and then back up to around $590 starting around 4am EST, reaching its lowest price around 7am and then returning to $590 around 10am.

Obviously this program's predictions are not always right, and predictions that are further away are more difficult for it to make. However, it seems relatively confident about this dip. I believe the dip will occur, though the magnitude may be a bit off or the dip may be shifted in one direction slightly. So we'll see how well the software performs!


Title: Re: Prepare for 4am dip
Post by: ShroomsKit_Disgrace on March 21, 2014, 04:44:05 PM
Nice stuff you have coded there!  :)


Title: Re: Prepare for 4am dip
Post by: MOB on March 21, 2014, 04:48:57 PM
Is that software called "English" and is the neural network "your brain"?


I agree that things tend to happen around certain times as different timezones wake up for the day, thereby setting a trend for other zones.


Title: Re: Prepare for 4am dip
Post by: Cyberlight on March 21, 2014, 05:04:06 PM
Why it didn't predict the China dip this morning ?

Average Error: 1.293% right.. nonsense.

It's just a tool for market manipulation.


Title: Re: Prepare for 4am dip
Post by: K128kevin on March 21, 2014, 05:16:59 PM
ShroomsKit_Disgrade - Thanks!

MOB - The software doesn't have a name because I didn't name it, and the neural network is an artificial neural network, not my brain. http://en.wikipedia.org/wiki/Artificial_neural_network It's a computational model for approximating functions basically.

Cyberlight -
1. It's not always right, as I said in the OP and as it says in multiple places on the website. It probably performs better than a human could though.
2. It did predict for the price to go down, just not to the degree that it did.
3. The average error is the amount off from the actual price that each price usually is. That means that with an average error of 1.3%, if the prediction is $600 then the price will usually be between $592.2 and $608.2. I explain how the average error is calculated in the about page.
4. The idea that I created this for market manipulation is beyond ridiculous for far too many reasons to name here...

*Also if something in China caused the price to go down, as what you said implied, then there is no way the software could predict that. I explain this in the section about real-life events on the about page.


Title: Re: Prepare for 4am dip
Post by: Cyberlight on March 21, 2014, 05:27:14 PM
Ok .. understand, but a head like 'Prepare for 4am dip' could suggest that, cosmofly is a obvious market manipulator.

What you predict is just a weekend dip, bitcoin has mostly always weekend dips.


Title: Re: Prepare for 4am dip
Post by: Ibian on March 21, 2014, 05:43:51 PM
Stop talking about cosmo already. It is unbelievable that a retard like that can have so much influence on people.


Title: Re: Prepare for 4am dip
Post by: Bonam on March 21, 2014, 06:03:13 PM
Neural networks aren't magic... all they can do is take data you supply them, process it in some way, and produce a result, just like any computer. If a neural network could be developed to predict future market movement based on past price data, you can be sure people would have already implemented it for the stock/futures/forex markets and made trillions of dollars.


Title: Re: Prepare for 4am dip
Post by: K128kevin on March 21, 2014, 06:31:57 PM
Neural networks aren't magic... all they can do is take data you supply them, process it in some way, and produce a result, just like any computer. If a neural network could be developed to predict future market movement based on past price data, you can be sure people would have already implemented it for the stock/futures/forex markets and made trillions of dollars.

Actually neural networks are very commonly used for stock predictions and they are known to be successful. You can buy software specifically for this purpose.

Check it out: http://en.wikipedia.org/wiki/Stock_market_prediction#Technical_analysis

Also I never said they are magic... Like I said, my software is sometimes wrong. It does seem to do pretty well though.


Title: Re: Prepare for 4am dip
Post by: Bonam on March 21, 2014, 06:52:47 PM
Actually neural networks are very commonly used for stock predictions and they are known to be successful. You can buy software specifically for this purpose.

If you can buy software that demonstrably gives you an edge, people will buy it and use it until any edge it gives evaporates, because whatever market inefficiency was being exploited will disappear.

You are right that you can make profit with ANNs, but only so long as your trades are small enough not to affect the market and as long as competitors don't have similar ANNs. I guess perhaps in the bitcoin world there is enough market inefficiency that you can do stuff like this without all the advantage evaporating immediately.


Title: Re: Prepare for 4am dip
Post by: segeln on March 21, 2014, 07:12:45 PM
Hi OP,
I am fascinated and i will watch the hole night,how your work will perform
Good Luck to you


Title: Re: Prepare for 4am dip
Post by: Torque on March 21, 2014, 07:35:14 PM
Hey guys, so I have a slightly more reasonable prediction than the "prepare for march 16th dip" post made a little while back.

As some of you may have seen in a post I made several days ago, I have been working on software that uses neural networks to predict bitcoin prices. The predictions can be seen at http://www.btcpredictions.com/

The short term neural network has been consistently predicting a dip from around $585 down to about $562 and then back up to around $590 starting around 4am EST, reaching its lowest price around 7am and then returning to $590 around 10am.

Obviously this program's predictions are not always right, and predictions that are further away are more difficult for it to make. However, it seems relatively confident about this dip. I believe the dip will occur, though the magnitude may be a bit off or the dip may be shifted in one direction slightly. So we'll see how well the software performs!

Let me translate the OP's text for everyone:

"Hey guys, I'm a newb that just create an account a few days ago.  I'm really a shark trader and/or whale that is trolling, but I'm going to pretend that I'm an innocent and I've got some amazing bitcoin TA powers so that people believe me.  I'm affiliated in some way or have insider knowledge of the group of whales that plan to post a fake FUD article about China banning bitcoin during the night.  It should happen around 4am EST.  When they do, the Chinese market is going to go into crazy panic sell off mode, and the price should [dip from around $585 down to about $562 and then back up to around $590 reaching its lowest price around 7am and then returning to $590 around 10am]. My cronies will then take advantage of the panic by scooping up cheap coins. But you'll think that somehow I have these amazingly predictive TA powers, and you'll give me kudos for being right and start following me in the Speculation forum.  You'll also think my neural net software is amazing, when it really doesn't do shit. Yay me and my cronies for conning you all."

 ::)



Title: Re: Prepare for 4am dip
Post by: K128kevin on March 21, 2014, 08:09:27 PM
segeln - thanks man! :D

Torque - I don't know what a shark trader or whale is, I don't know what a FUD article is, I don't know what half the things you said even are. I spent hundreds, if not thousands of hours working on the software that creates this, and I never said that I have some amazing predicting powers. In fact, I have been continually warning people that this can sometimes be wrong - there is no guarantee here. You obviously did not read anything I wrote on my site. Please don't make ridiculous accusations towards me based on literally nothing -_-

Also I'm not working with anyone else on this - it's just me at the moment.


Title: Re: Prepare for 4am dip
Post by: Torque on March 21, 2014, 08:13:54 PM
segeln - thanks man! :D

Torque - I don't know what a shark trader or whale is, I don't know what a FUD article is, I don't know what half the things you said even are. I spent hundreds, if not thousands of hours working on the software that creates this, and I never said that I have some amazing predicting powers. In fact, I have been continually warning people that this can sometimes be wrong - there is no guarantee here. You obviously did not read anything I wrote on my site. Please don't make ridiculous accusations towards me based on literally nothing -_-

Also I'm not working with anyone else on this - it's just me at the moment.
Posted so you can't edit.  Your first and second sentences clearly incriminate you.  You don't know what those things are, but you've put 1000's of hours of time into a neural net prediction engine for bitcoin?  Riiiight.


Title: Re: Prepare for 4am dip
Post by: Ibian on March 21, 2014, 08:14:42 PM
I don't even like clicking the ignore button, why some people make me do it :(


Title: Re: Prepare for 4am dip
Post by: counter on March 21, 2014, 08:15:01 PM
thanks for the heads up friend but if you are way off by 20 hours are you still going to claim that your predictions are spot on?  ;D


Title: Re: Prepare for 4am dip
Post by: BitcoinHawker on March 21, 2014, 08:18:11 PM
Hey guys, so I have a slightly more reasonable prediction than the "prepare for march 16th dip" post made a little while back.

As some of you may have seen in a post I made several days ago, I have been working on software that uses neural networks to predict bitcoin prices. The predictions can be seen at http://www.btcpredictions.com/

The short term neural network has been consistently predicting a dip from around $585 down to about $562 and then back up to around $590 starting around 4am EST, reaching its lowest price around 7am and then returning to $590 around 10am.

Obviously this program's predictions are not always right, and predictions that are further away are more difficult for it to make. However, it seems relatively confident about this dip. I believe the dip will occur, though the magnitude may be a bit off or the dip may be shifted in one direction slightly. So we'll see how well the software performs!

Good luck! I hope it works. I am just a hodler ;)


Title: Re: Prepare for 4am dip
Post by: segeln on March 21, 2014, 08:21:43 PM

Let me translate the OP's text for everyone:

"Hey guys, I'm a newb that just create an account a few days ago.  I'm really a shark trader and/or whale that is trolling, but I'm going to pretend that I'm an innocent and I've got some amazing bitcoin TA powers so that people believe me.  I'm affiliated in some way or have insider knowledge of the group of whales that plan to post a fake FUD article about China banning bitcoin during the night.  It should happen around 4am EST.  When they do, the Chinese market is going to go into crazy panic sell off mode, and the price should [dip from around $585 down to about $562 and then back up to around $590 reaching its lowest price around 7am and then returning to $590 around 10am]. My cronies will then take advantage of the panic by scooping up cheap coins. But you'll think that somehow I have these amazingly predictive TA powers, and you'll give me kudos for being right and start following me in the Speculation forum.  You'll also think my neural net software is amazing, when it really doesn't do shit. Yay me and my cronies for conning you all."

sounds like conspiracy theory
any proofs or evidence ?


Title: Re: Prepare for 4am dip
Post by: K128kevin on March 21, 2014, 08:24:58 PM
Haha I will call the prediction successful if it happens within like +/- 3 hours maybe, but no more than that. Certainly not 20 haha

Torque - This is a computer science project, I don't need to know a lot about economics to program a decent neural network. If you dislike my project then ignore it, there is no need to come here and insult me and my work for no reason. At least give constructive criticism if you don't like it - that I would be open to.


Title: Re: Prepare for 4am dip
Post by: vitarian on March 21, 2014, 09:41:04 PM
Stop talking about cosmo already. It is unbelievable that a retard like that can have so much influence on people.

hey, it wasn't cosmo, it was cosmo's friend of a friend.


Title: Re: Prepare for 4am dip
Post by: segeln on March 22, 2014, 07:35:10 AM
hey guys,
I don`t think it`s fair to discredit an idea that has to be proved by reality. Give it a Chance ! Today is a good Chance for proving since the Price-swing is more then the statistical error in the model (based on the actual prediction,not on updated ones every hour). Wait 5 hours


Title: Re: Prepare for 4am dip
Post by: Zule on March 22, 2014, 07:40:12 AM
This is so much better than cosmo's dip. Its based on statistics which is better than retard math.
I wish for this call to be a huge hit, and the thread to reach 40 pages.


Title: Re: Prepare for 4am dip
Post by: threecats on March 22, 2014, 08:00:56 AM
happening now : -)


Title: Re: Prepare for 4am dip
Post by: chessnut on March 22, 2014, 08:02:49 AM
wow this call was almost as accurate as cosmoflys call.

cosmofly is certainly not alone being a top financial forecast expert on this forum. he is certainly highly regarded by even the best.


Title: Re: Prepare for 4am dip
Post by: Zule on March 22, 2014, 08:38:15 AM
wow this call was almost as accurate as cosmoflys call.

cosmofly is certainly not alone being a top financial forecast expert on this forum. he is certainly highly regarded by even the best.

I see what you are doing there... ::)


Title: Re: Prepare for 4am dip
Post by: Cassius on March 22, 2014, 09:06:08 AM
Hey guys, so I have a slightly more reasonable prediction than the "prepare for march 16th dip" post made a little while back.

As some of you may have seen in a post I made several days ago, I have been working on software that uses neural networks to predict bitcoin prices. The predictions can be seen at http://www.btcpredictions.com/

The short term neural network has been consistently predicting a dip from around $585 down to about $562 and then back up to around $590 starting around 4am EST, reaching its lowest price around 7am and then returning to $590 around 10am.

Obviously this program's predictions are not always right, and predictions that are further away are more difficult for it to make. However, it seems relatively confident about this dip. I believe the dip will occur, though the magnitude may be a bit off or the dip may be shifted in one direction slightly. So we'll see how well the software performs!

Let me translate the OP's text for everyone:

"Hey guys, I'm a newb that just create an account a few days ago.  I'm really a shark trader and/or whale that is trolling, but I'm going to pretend that I'm an innocent and I've got some amazing bitcoin TA powers so that people believe me.  I'm affiliated in some way or have insider knowledge of the group of whales that plan to post a fake FUD article about China banning bitcoin during the night.  It should happen around 4am EST.  When they do, the Chinese market is going to go into crazy panic sell off mode, and the price should [dip from around $585 down to about $562 and then back up to around $590 reaching its lowest price around 7am and then returning to $590 around 10am]. My cronies will then take advantage of the panic by scooping up cheap coins. But you'll think that somehow I have these amazingly predictive TA powers, and you'll give me kudos for being right and start following me in the Speculation forum.  You'll also think my neural net software is amazing, when it really doesn't do shit. Yay me and my cronies for conning you all."

 ::)



Seriously?!
Grow up.


Title: Re: Prepare for 4am dip
Post by: K128kevin on March 22, 2014, 01:35:07 PM
Well I just woke up and looked at the charts - it looks like the price definitely started dipping down around 3am (1 hour earlier than I predicted) so I'll call that half of the prediction a success. It has yet to rise back up again but we'll see. Like I said, it may get the magnitude wrong or it may shift slightly in one direction or the other. The price seems to be behaving reasonably close to what the model predicted though.


Title: Re: Prepare for 4am dip
Post by: segeln on March 22, 2014, 02:25:35 PM
Well I just woke up and looked at the charts - it looks like the price definitely started dipping down around 3am (1 hour earlier than I predicted) so I'll call that half of the prediction a success. It has yet to rise back up again but we'll see. Like I said, it may get the magnitude wrong or it may shift slightly in one direction or the other. The price seems to be behaving reasonably close to what the model predicted though.
you are right half an hour ist ok.I checked the movements from today morning up to now. I am not disappointed.Go ahead und again good luck.
BTW: do you have any scientific Background? Which one?


Title: Re: Prepare for 4am dip
Post by: akujin on March 22, 2014, 03:14:34 PM
fail... imagine buying at 562.... thinking it'll head back at 590  ;D
but it's at 555 right now  ;D


Title: Re: Prepare for 4am dip
Post by: segeln on March 22, 2014, 03:19:05 PM
fail... imagine buying at 562.... thinking it'll head back at 590  ;D
but it's at 555 right now  ;D
first fail today
but interesting to follow the reliability of the predictions


Title: Re: Prepare for 4am dip
Post by: K128kevin on March 22, 2014, 03:39:51 PM
So yeah the price hasn't gone back up yet. Maybe it will, maybe it won't - the software seems to have changed its mind and is now predicting that the price won't go back up immediately. So the prediction was not entirely accurate, but I would say it was at least semi-successful. It was pretty accurate about the initial fall in price.


Title: Re: Prepare for 4am dip
Post by: segeln on March 22, 2014, 04:35:55 PM
So yeah the price hasn't gone back up yet. Maybe it will, maybe it won't - the software seems to have changed its mind and is now predicting that the price won't go back up immediately. So the prediction was not entirely accurate, but I would say it was at least semi-successful. It was pretty accurate about the initial fall in price.
well,I know that coumpterbased simulations/predictions rely on the reliability and validity of Input data.Perhaps you have to adjust and reconsider the data.
Next: if you make updates every 5 or even 1 Minute the prediction should get more accurate since the Computer can respond more quickly to changing datas(which you have reconsidered about reliability and validity).The data are changing in a quickly manner in the BTC- Environment


Title: Re: Prepare for 4am dip
Post by: zimmah on March 22, 2014, 05:28:35 PM
May be a little OCD, but could you make the lines on the graph sync up with numbers that end in 5 or 10. Like 600, 605, 610, etc. I know it is arbitrary, but...

why the hate on 14?


Title: Re: Prepare for 4am dip
Post by: oda.krell on March 22, 2014, 05:57:26 PM
There's way too much unwarranted hate directed towards K128kevin and accusations of FUD. To which I'd like to say: Shut the fuck up, guys. Be grateful that at least /some/ people in here post minimally more intellectually challenging stuff than pictures of bears or rockets going to the moon.

That said, I'm very skeptical a simple ANN trained on price diff is of much use for actual trading decisions. It'll probably work okay for days with little volatility, but it's almost certainly too crude to in any reliable way predict major trend changes. Sorry OP.


Title: Re: Prepare for 4am dip
Post by: K128kevin on March 22, 2014, 06:23:39 PM
dhomstad - haha yeah it is a bit weird. Creating those graphs was very tricky actually, making it so that it automatically adjusts the intervals and prices to fit to the data... I could work on making it have only 5 or 0 at the end of each interval and I might at some point. However, it's pretty low on my priority list... it is a lot of work for a small improvement.

segeln - Yeah you're right that the data is changing quickly. I might be able to make it update more often, but definitely not every one minute. The smallest interval I could probably do would be every like 10 minutes. Right now it takes the software something like 60-90 ish seconds to run, so it wouldn't be able to run every minute. It could theoretically do every 5 minutes, but I want to leave extra space because I may need it to make more calculations if I add longer predictions to the site.

Oh and I don't really have scientific background unless you count computer science lol... I'm studying computer science at college and I'll be graduating this May.

oda.krell - Thanks lol... and as far as your skepticism, it is not unwarranted. I haven't yet tested this a lot in practice. I do think you would be hard pressed to find a more reliable means of predicting prices though. So far it has been reasonably accurate, but I guess the true test will be when the price really starts becoming more volatile.

I believe that a neural network is capable of relatively accurately predicting prices when they become volatile - the question is whether or not this neural network can, or if I need to change the way it is structured/trained.

**Another interesting thing to note about the way this works though, is that over time this model will become more and more accurate. Bitcoins are still very new and there is not a lot of data to use for discerning patterns. As time goes on, more data will be available and so the neural network will be able to make a more informed prediction.


Title: Re: Prepare for 4am dip
Post by: GigaCoin on March 22, 2014, 06:31:46 PM
Nice call on that $2 dip, I predict we will dip by $1 in the next hour  :D

Jokes aside its more important to predict or analyze a trend rather than just calling a dip at 4am, which didnt happen, and even if you think it did, it was to no one's benefit. Which is why I think this thread is pointless, no offense.


Title: Re: Prepare for 4am dip
Post by: Cassius on March 22, 2014, 06:37:09 PM
I'd be interested to see 5-day to 1-month predictions, no matter how inaccurate. One of the fun things about projects like this is the incremental improvements that happen as you implement new features.
Cool project, anyway, and will look forward to seeing how it develops.


Title: Re: Prepare for 4am dip
Post by: K128kevin on March 22, 2014, 06:46:50 PM
GigaCoin - This method of prediction is not perfect (no method is or ever will be) but it definitely did call a drop in price, which did occur. It may have gotten some of the specific figures wrong, but the trend was correct (which as you said yourself, is what's most important). See the image below - the price dropped one hour earlier than the neural network predicted, and it reached its lowest point almost exactly when it predicted. I'll admit it was completely wrong about the rise in price that would occur after the dip, but I don't think you can just call this chance - this was accurately predicted.

http://www.btcpredictions.com/predictedprice.png

Cassius - Thanks! Yeah I would like to add some longer-term predictions. I'll probably work on that over the next week or so... might even be able to get it up sooner.


Title: Re: Prepare for 4am dip
Post by: segeln on March 22, 2014, 07:11:43 PM
segeln - Yeah you're right that the data is changing quickly. I might be able to make it update more often, but definitely not every one minute. The smallest interval I could probably do would be every like 10 minutes. Right now it takes the software something like 60-90 ish seconds to run, so it wouldn't be able to run every minute. It could theoretically do every 5 minutes, but I want to leave extra space because I may need it to make more calculations if I add longer predictions to the site.

Oh and I don't really have scientific background unless you count computer science lol... I'm studying computer science at college and I'll be graduating this May.
thanks for the answer.I will repeat. MOST IMPORTANT ARE RELIABLE AND VALID Data to predict something.Hope you will find them-I can`T supply,sorry


Title: Re: Prepare for 4am dip
Post by: segeln on March 22, 2014, 07:31:08 PM
There's way too much unwarranted hate directed towards K128kevin and accusations of FUD. To which I'd like to say: Shut the fuck up, guys. Be grateful that at least /some/ people in here post minimally more intellectually challenging stuff than pictures of bears or rockets going to the moon.
a post you deserve even from me  +1