Topic: Methods of Prediction (Read 1457 times)

hahaha I had no idea what you guys were talking about and then I read the "Prepare for March 16th dip" thread... LOL that was ridiculous

You've got a point! Haha! Oh the power of a negative indicator! Maybe that's the ruse the whole time.

[Admittedly though, in terms of probabilities, because of the types of predictions made and using the relative volatility in the markets, it's more likely for 100% fail rate to happen than a 100% success rate. Still though, in terms of usefulness they're equal.]

actually, a 100% failure rate is just as impressive, and would be an infinitely useful contrarian indicator

+1

This is probably the best method to employ. It has been shown to be 100% all of the time. You can't beat 100%. Sure it's a 100% fail rate, but it's all good right?

The method that I use is a combination of averages, moving averages, automatically adjusting tables and targeting. (A bunch of baselines calculated from some other financial methods compounded with PivotTables hehe.)

My favorite method is to listen to cosmofly's autistic friend.

Reading charts whilst being up to date with the latest news.
If you've heard speculation regarding BTC that will portray it negatively, predict a fall. (However, look at graph trends as well to predict the next natural shape of the graph should all factors remain constant - ie no bad news).

I'm glad you are interested and I'd be happy to keep you guys up to date! And I'll definitely check out that book.

The people who predicted $1,000+/BTC were NUTS, until it really happened.
I predict many more surprises ahead.   

It would be interesting if you kept us appraised of your progress. I would definitely find it interesting.

A great free online textbook for forecasting:  https://www.otexts.org/fpp

I use a forward feed neural network with backpropogation. There are actually two neural networks - one for short term and one for long term. They both have three layers (inputs, hidden layer, outputs) and they use the same activation function (sigmoid). Basically the only difference between them is the number of nodes in each layer, and the data I give them. The long term neural network uses 80 inputs and 20 outputs, which each correspond with changes in average price over 6 hour periods. The short term neural network uses 60 inputs and 24 outputs, which each correspond with changes in average price over 1 hour periods. Both have hidden layers with 200 nodes.

Knightcoin - That documentary looks so awesome! I am definitely going to find the full version of that and watch it!

I don't really know any other forecasting methods. I basically just used neural networks because I learned about them in a class I took a few semesters ago and thought they were really interesting. We used them to recognize hand-written digits and when I found out that they are often used for stock price prediction I decided it would be a cool idea to use them for bitcoin price prediction.

I've never heard of ARIMA but I will check that out for sure. Like I said, I don't really know any other forecasting methods but I do know that they exist. That's largely why I created this thread.

I think a lot of the major spikes or crashes in bitcoin price are probably nearly unpredictable since it obviously is very fundamentally unstable. However, I would think that it would be possible to (once a spike or crash is occurring) predict how exactly the event would play out as far as bitcoin prices go. Once a major event occurs that causes bitcoin prices to fall or spike, I feel like there must be some discernible patterns in price changes.

Or maybe not, who knows lol

ARIMA (auto-regressive, integral, moving average) or Box-Jenkins was state of the art a dozen years ago.  Now, harder to say, but basically what organ said, given how fundamentally unstable the bitcoin market is, very hard to use technical analysis.

https://www.youtube.com/watch?v=5RAtFSEkFho

I use the tried-and-true Nostradamus method.

OP: what sorts of forecast methods have you considered? Also, it doesn't seem to me that bitcoin prices would be the sort of recurring data that neural nets tend to like? (for example sunspot activity)

I've used exponential smoothing and ARIMA models before. They'll model a calm market ok, but don't model volatility well before a large change in price.

I've also tried using GARCH models, but I need to work with these a bit more. I think that's at least one model you probably should be seriously considering.

Glad to see your post OP. I always like to see less common approaches to TA.

Care to elaborate a bit on your ANN method? How many layers? Regular feedforward ANN or recurrent network? What's the input and history size you train on?

How do we predict weather ?

Yeah, I pretty much just hold at the moment too although that's mostly because I don't have enough extra money floating around to risk buying/selling in short intervals. I think you definitely need to consider the news whether you are following some type of technical analysis or just going on your intuition. And yeah I think neural networks are very interesting (obviously)!

Bitcoin is definitely far from a normal market, which is why it's so risky to try to make money by buying/selling in short intervals. But I'm sure people do it, and I'm wondering if they are just lucky or if they have some strategies. And I'd be curious to see if there is some way to measure their performance in comparison to buying/selling based on a model like mine.

Also btw the time zone on the charts is your current time zone.

I hodl.

As for prediction I think news is also a indicator that should be considered.
Trading on traditional technical analysis is risky since bitcoin is no normal market and is being manipulated.

If anything can work neural networks could. Also they are interesting.
Wish you the best of luck!

Nice work, you should put the timezone for reference