Prepare for 4am dip

[segeln]

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

[Zule]

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.

[threecats]

happening now : -)

[chessnut]

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.

[Zule]

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...

[Cassius]

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.

[K128kevin]

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.

[segeln]

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?

[akujin]

fail... imagine buying at 562.... thinking it'll head back at 590 
but it's at 555 right now 

[segeln]

fail... imagine buying at 562.... thinking it'll head back at 590 
but it's at 555 right now 

first fail today
but interesting to follow the reliability of the predictions

[K128kevin]

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.

[segeln]

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

[zimmah]

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?

[oda.krell]

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.

[K128kevin]

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.

[GigaCoin]

Nice call on that $2 dip, I predict we will dip by $1 in the next hour  

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.

[Cassius]

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.

[K128kevin]

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.



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.

[segeln]

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

[segeln]

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