Ideal buy/sell strategy for maximizing profit

[maker88]

Looks like that buy went through

Yup! Although it did go down to $550. However, I think when we look back at these charts we'll see that $575 was probably a decent price to buy at.

I wonder how many people actually sold @ 550

575 was definitely much better for the sake of liquidity

i bought some at 550, some someone did

[K128kevin2]

i bought some at 550, some someone did

Nice dude! Yeah when I was watching it I thought it was going to go a bit below $575, but I thought the bottom would be like $560. I didn't think it would go down to $550 but good job, that's right on the money (figuratively and kind of literally )

[K128kevin2]

looks like $575 was a pretty decent time to buy

[porcupine87]

Sometimes it does lose money. Of the 31 30-day periods tested, it lost money during 9, broke even during 5, and gained money during the other 17. However keep in mind that this is still all predictive, so there is no guarantee of anything.

So know you really tested it, not only on test data. I still wonder if we had a misunderstanding the last time or if you were wrong. Acutually I have a name for this now. It is called overfitting. If you use let's say 10 neurons and get an error of 2% you will never make that error smaller with adding another neuron. It is the same with the linear regression. If you add complete random variables, R² will never decrease. But the model will be more useless for new data.

But I never said your neural network is worse that the normal technical analysis. Probably better.

I check this out. $625 in 24h.

[seleme]

Doesn't send confirmation mails at all.

[trip96]

I love your work with this neural networking predictions. Great work on constantly making it more accurate and presenting info in new ways. I congratulate you on your success so far.

NOW! I want a couple things. (heheheheh greedy forum member.)

IF it's possible I'd love to see:

1. API

2. Whitepaper

If i can help in any way too I'd be down.

Thanks again for this awesome tool to use as a trade signal for the BTC.

[porcupine87]

Doesn't send confirmation mails at all.

It sent to me just a minute ago. I have gmail...

[K128kevin2]

So know you really tested it, not only on test data. I still wonder if we had a misunderstanding the last time or if you were wrong. Acutually I have a name for this now. It is called overfitting. If you use let's say 10 neurons and get an error of 2% you will never make that error smaller with adding another neuron. It is the same with the linear regression. If you add complete random variables, R² will never decrease. But the model will be more useless for new data.

But I never said your neural network is worse that the normal technical analysis. Probably better.

I check this out. $625 in 24h.

Hey so I'm not sure I quite understand what you are saying here. Can you remind me what we were talking about in our last conversation? Sorry lol...

Doesn't send confirmation mails at all.

Sorry, it has trouble with Hotmail and occasionally with some other less common emails. Send an email to BTCPredictions@gmail.com from the email that you signed up with and I can get your account activated.

I love your work with this neural networking predictions. Great work on constantly making it more accurate and presenting info in new ways. I congratulate you on your success so far.

NOW! I want a couple things. (heheheheh greedy forum member.)

IF it's possible I'd love to see:

1. API

2. Whitepaper

If i can help in any way too I'd be down.

Thanks again for this awesome tool to use as a trade signal for the BTC.

I'm glad you like it! What would you be looking for in an API? And by whitepaper do you mean to make the algorithm open source?

[porcupine87]

So know you really tested it, not only on test data. I still wonder if we had a misunderstanding the last time or if you were wrong. Acutually I have a name for this now. It is called overfitting. If you use let's say 10 neurons and get an error of 2% you will never make that error smaller with adding another neuron. It is the same with the linear regression. If you add complete random variables, R² will never decrease. But the model will be more useless for new data.

But I never said your neural network is worse that the normal technical analysis. Probably better.

I check this out. $625 in 24h.

Hey so I'm not sure I quite understand what you are saying here. Can you remind me what we were talking about in our last conversation? Sorry lol...

Sorry. I was interested and amazed by the low average error. So I wanted to test this. I took 6 or 7 random points in time and wrote your 24h prediction down. After 24hours I checked the real value. I measured an error of 8%, not 1.2% like your average error. There were two possible explainations for that:
1. Your average error is the error of your learning data and useless for real predictions.
2. I was very unlucky. Very Very unlucky. Rolling a dice 6 times in a row and get an 1 all the time is more possible.

Anyhow. Is it a secret how far you go back in time for the learning? How many neurons do you use?

[K128kevin2]

Sorry. I was interested and amazed by the low average error. So I wanted to test this. I took 6 or 7 random points in time and wrote your 24h prediction down. After 24hours I checked the real value. I measured an error of 8%, not 1.2% like your average error. There were two possible explainations for that:
1. Your average error is the error of your learning data and useless for real predictions.
2. I was very unlucky. Very Very unlucky. Rolling a dice 6 times in a row and get an 1 all the time is more possible.

Anyhow. Is it a secret how far you go back in time for the learning? How many neurons do you use?

Ugh I remember that conversation... I do not want to get back into that again.

For the new app, the neural network looks at prices in like 5 min intervals for the past couple hours, hour intervals for the past like 1.5 ish days I think, and like every other day I think for the past about 30 days. I don't remember exactly because I trained it a while ago, although I have the exact parameters written down somewhere.

There are 65 inputs, 30 hidden nodes, and 2 output nodes.

[trip96]

For API I would love to simply have the updated buy and sell prices. But thinking of it I can probably grab those and parse them into a program from your site anyways. Maybe if you made a JSON page that would be just as good.

By Whitepaper I mean your ideas and thinking behind your algorithms and specifics on how they actually work. SO yes open source along with the conceptual or philosophical reasoning as well.

Thanks again for your work and contribution to the community!

[K128kevin2]

For API I would love to simply have the updated buy and sell prices. But thinking of it I can probably grab those and parse them into a program from your site anyways. Maybe if you made a JSON page that would be just as good.

By Whitepaper I mean your ideas and thinking behind your algorithms and specifics on how they actually work. SO yes open source along with the conceptual or philosophical reasoning as well.

Thanks again for your work and contribution to the community!

I spoke to some people today at Coinalytics (bitcoin startup out in California). They may be developing an API for this data actually!

For now the code is not going to be open source yet, but I am thinking about developing some open source trading algorithms. Maybe I'll develop like a framework for simulating trade based on any strategy and make it easy to implement and test different strategies. It could be interesting to see what kinds of strategies people come up with.

Also on an unrelated note, here is a picture of the profitability of trading based on the data on this new section of the site versus just buying and holding:


EDIT: The values on the left are in USD, so if it is currently holding bitcoin instead of USD it just multiplies number of bitcoins held times the value of bitcoin.

[mybitcoincharts]

Absolutely ridiculous. Let's see the real time graph of buy and hold vs your neural network, not a simulated profits from the past graph.

Huh? What do you mean with real time graph? Pofits with buy and hold obviously equal price development. +100x price development = +100x profit. What should be simulated about that?

[elebit]

Huh? What do you mean with real time graph? Pofits with buy and hold obviously equal price development. +100x price development = +100x profit. What should be simulated about that?

The only thing that matters is future profits.

Decide on your algorithm now, and come back in a week (.. month, or year) and tell us how much it actually could have made.

It is trivial to find and algorithm have would have traded for immense profits historically. I know if could do much "better" than what the author published above, only by following known fixpoints. But that strategy would not own me even a millibitcoin in the future.

And netiher would the author's. Or...? The proof is in the pudding, as they say.

[mybitcoincharts]

The only thing that matters is future profits.

Decide on your algorithm now, and come back in a week (.. month, or year) and tell us how much it actually could have made.

It is trivial to find and algorithm have would have traded for immense profits historically. I know if could do much "better" than what the author published above, only by following known fixpoints. But that strategy would not own me even a millibitcoin in the future.

And netiher would the author's. Or...? The proof is in the pudding, as they say.

Thx, now I got what was meant. The term I know for that is prognostic validity. Backtesting the algorithm is a necessary first step, though. If it fails generating profit on past data the probability of doing it in the future is rather slim.

[K128kevin2]

The only thing that matters is future profits.

Decide on your algorithm now, and come back in a week (.. month, or year) and tell us how much it actually could have made.

It is trivial to find and algorithm have would have traded for immense profits historically. I know if could do much "better" than what the author published above, only by following known fixpoints. But that strategy would not own me even a millibitcoin in the future.

And netiher would the author's. Or...? The proof is in the pudding, as they say.

I can see what you are saying but I think maybe you misunderstand what I'm doing when I simulate trade. The neural network that looks at the historic data has no idea where the price is going to go when it simulates trade. It doesn't know pre-determined ideal points of where to sell or buy - it basically uses a formula (or more accurately, a function) to determine when it is good to buy or sell, and it makes these decisions on the fly with no knowledge of what will happen next (as would be the case with future data). It's purely based on recent prices. Also I can assure you that creating a trading strategy that can do this and be profitable on historic data is very far from trivial lol... it takes a ton of time, work, and effort.

[jayc89]

For API I would love to simply have the updated buy and sell prices. But thinking of it I can probably grab those and parse them into a program from your site anyways. Maybe if you made a JSON page that would be just as good.

By Whitepaper I mean your ideas and thinking behind your algorithms and specifics on how they actually work. SO yes open source along with the conceptual or philosophical reasoning as well.

Thanks again for your work and contribution to the community!

Agreed.

I'm working on a simplistic trading bot. It would be great to integrate this sort of prediction into the bot, rather than me trying to hack together some sort of trending logic

[oda.krell]

Just out of curiosity: the data used to determine the profitability of the network's outputs wasn't used in the training phase of the network, correct?

[K128kevin2]

Just out of curiosity: the data used to determine the profitability of the network's outputs wasn't used in the training phase of the network, correct?

I've tested it on the same data and on different data, and the results are very similar. The issue with training and testing on the same data is generally overfitting, but overfitting is impossible with this model. The testing I've done with neural networks on future data has yielded pretty much the same results as tests on historic data.

[oda.krell]

Just out of curiosity: the data used to determine the profitability of the network's outputs wasn't used in the training phase of the network, correct?

I've tested it on the same data and on different data, and the results are very similar. The issue with training and testing on the same data is generally overfitting, but overfitting is impossible with this model. The testing I've done with neural networks on future data has yielded pretty much the same results as tests on historic data.

You mean you have few enough model parameters to make overfitting the given data unlikely. Yes?

This still allows for subtle effects how well your network generalizes to new input, especially for something as error sensitive as trading. There's a reason why in ML the data is usually partitioned into a training set and a test set (or three, including a validation set), and the two are kept separate.