Author

Topic: Using multiple MatLab curve fittings on Bitcoin historical price data (Read 228 times)

legendary
Activity: 1638
Merit: 1163
Where is my ring of blades...


this last chart here has been one of the oldest charts that existed for a long time for bitcoin predicting the future prices in respect to their time. and surprisingly enough we have been hitting most of the targets so far with each of the rallies that bitcoin has.
but still I wouldn't rely on it for speculation though because we all know that the volatility is always changing. nobody was predicting the surge to $20k but it easily happened.
legendary
Activity: 1372
Merit: 1032
All I know is that I know nothing.
just like what i said by the end of 2017 about the drop i will repeat the same thing about the rise in 2019+ too. there is no reason to see the repetition of the same trends which means your charts don't have to be true at all. you are basically extrapolating data which is not the best indicator for the future price.
with that said we have seen the same thing be repeated as many investors back in 2017 started to believe that such repetitions exist! so they mostly forced the repetition of 2013 drop.
for this following rise the same thing can happen only if they force the same thing to happen!!! otherwise the market is so much bigger and is moving at a much faster pace. so it should take a lot less time to reach the $100k bubble this time.
hero member
Activity: 2870
Merit: 574
Vave.com - Crypto Casino
You have done a good job to make that chart, and I am sure that you are good too in predicting bitcoin price.
But still, that is a prediction which we don't know if that will happen or not since the market has moved up and down in every day.
The only we can do is observe on the market directly and analyzing the bitcoin price history will give us a sign about what will happen in the next moment.
But once again, no one will know what will happen in this month, in the next month even in the next year.
If you are trading bitcoin pair fiat, then make sure that you can take a profit by using so many analysis and chart.
For me, that calculation using MatLab will be too complicated since I am not good in the math calculation.
legendary
Activity: 3472
Merit: 10611
this is a nice effort and you have obviously spent some time on this but the problem is that the market is not something you could predict with math! we are talking about a dynamic thing that takes effect from the decisions millions of people are going to make in the future. in other words the rise you predict is the adoption and there is no way we can know how adoption is going to be like in the future. if nothing changes then your prediction is closest to reality but things don't remain the same.
for instance what if Amazon, eBay,... and some of those other giants started adding bitcoin to their platforms? price would simply shoot up to the moon within a couple of months.
hero member
Activity: 672
Merit: 526
Interesting. But eventually, all the comparisons with the past, will suggest that Bitcoin will be worth more than it was worth and that the growth will be constant. But the risk, is not in knowing when it will be worth more than ATH. The risk is whether it will be worth more than it is today and for how long it will stay far away from zero.
member
Activity: 616
Merit: 12
Send&Receive Money Instantly, w/ no hidden costs
An analysis that is quite convincing, but in the end the average of the various methods that we use more misses the analysis even when they say that the price of bitcoin has passed the support price.
legendary
Activity: 3668
Merit: 6382
Looking for campaign manager? Contact icopress!
I like the fact you've started with TL;DR;   Grin
The conclusions are nice for all the holders, (and they do look convincing too) however, we all know that nobody can predict the future. Those graphs can be pretty accurate or can be very inaccurate, only time will tell if you were right or not.

Some strange news triggering a big and long new dump or some great news with a sudden pump may have as result the need to revise the graphs and the results.
Of course, in theory we are good now, since we've got the golden cross...
sr. member
Activity: 625
Merit: 258
That's such a good draft  for creating price speculations theories.

It really feels just the way Bitcoin has evolved since the beginning. Still we don't need such graphs to understand what can happen in the future if those trends continue.
Unless some governmental big decision stops from bitcoin to ever exist (which is not likely to happen) i don't see price being slowed down which proves those curves.
member
Activity: 187
Merit: 45
One of the most interesting analyzes of recent years. Thank you so much for sharing and for your great work.

There is no doubt that regardless of any result obtained, this is based on analysis of past data and that therefore forecasting the future is always a bit of a mystery, and that you obviously cannot foresee events that can radically change the price in the short term.

however very very interesting
hero member
Activity: 3178
Merit: 977
www.Crypto.Games: Multiple coins, multiple games
Honestly, I don't have any problem with the results and would be completely satisfied if BTC hits those values in the time frames that you mentioned. This would mean that is is growing in an organic manner which is great for the crypto ecosystem overall.
member
Activity: 93
Merit: 41

The "depressing" TL;DR clickbait:
- We will stay below 11,500 for the rest of 2019
- The earliest we can get back near 20,000 is around Dec 2020
- The earliest we can see 100,000 is around Mar 2024


----------

I've seen several approaches to curve fitting applied to price data such as those by @Awe_andWonder (e.g. https://twitter.com/awe_andwonder/status/1029461906753576960, in this case applied to total market cap), and thought I'ld try a variation of the usual curve fitting.

Instead of applying a single curve fit to the entirety of the price data, what I'll do is apply multiple curve fits to sets of the data up to a certain dates and then see how those historical curve fits then compare to the actual price action which occurred. This way I can see how well a curve fit for a set of data up to a certain date predicted the subsequent price movement.

Raw price daily data was taken from bitinfocharts.com (starting from Jul 17, 2010), and curve fitting was performed using MatLab's curve fitting tool with a 2-term power equation selected (MatLab results/equations will be provided below), with the the common logarithm taken of the raw data prior to curve fitting.

I'll be performing curve fits on the following sets of price data (according to the major bull runs of Bitcoin):

(1) Price data from start (07/17/10) till the low right before the 2011 bull run. This curve fit will then be compared to the price action during the 2011 bull run.
(2) Price data from start (07/17/10) till the low right before the 2013 bull run. This curve fit will then be compared to the price action during the 2013 bull run.
(3) Price data from start (07/17/10) till the low right before the 2017 bull run. This curve fit will then be compared to the price action during the 2017 bull run.

----------

Curve fit compared to 2011 bull run

Starting with the first set of data, apply a curve fit to the data from the period of 170 days after 07/17/10. The result is the following:

Quote
General model Power2:
     f(x) = a*x^b+c
Coefficients (with 95% confidence bounds):
       a =   0.0002096  (-0.0001077, 0.000527)
       b =       1.618  (1.323, 1.912)
       c =      -1.269  (-1.316, -1.222)

Goodness of fit:
  SSE: 2.289
  R-square: 0.8298
  Adjusted R-square: 0.8278
  RMSE: 0.1171

With the following graph (x-axis are number of days since Jul 17, 2010; y-axis is the Bitcoin price on a logarithmic scale):



Then add in the actual price action which occured during the 2011 bull run, resulting in this graph:



Notice how the subsequest price action was almost all underneath the projected curve fit line based on the data prior to the 2011 bull run.

----------

Curve fit compared to 2013 bull run

Moving on to the second set of data, apply a curve fit to the data from the period of 502 days after 07/17/10. The result is the following:

Quote
General model Power2:
     f(x) = a*x^b+c
Coefficients (with 95% confidence bounds):
       a =     0.05914  (0.01967, 0.09861)
       b =      0.6255  (0.5271, 0.724)
       c =      -1.771  (-1.991, -1.551)

Goodness of fit:
  SSE: 66.2
  R-square: 0.8062
  Adjusted R-square: 0.8054
  RMSE: 0.3642

With the following graph (x-axis is the number of days since Jul 17, 2010; y-axis is the Bitcoin price on a logarithmic scale):



Then add in the actual price action which occured during the 2013 bull run, resulting in this graph:



Notice how the subsequest price action was completely underneath the projected curve fit line based on the data prior to the 2013 bull run.

----------

Curve fit compared to 2017 bull run

Finally for the third set of data, apply a curve fit to the data from the period of 1660 days after 07/17/10. The result is the following:

Quote
General model Power2:
     f(x) = a*x^b+c
Coefficients (with 95% confidence bounds):
       a =     0.06375  (0.04671, 0.08078)
       b =      0.5742  (0.5411, 0.6073)
       c =      -1.571  (-1.701, -1.441)

Goodness of fit:
  SSE: 210.6
  R-square: 0.9081
  Adjusted R-square: 0.908
  RMSE: 0.3565

With the following graph (x-axis is the number of days since Jul 17, 2010; y-axis is the Bitcoin price on a logarithmic scale):



Then add in the actual price action which occured during the 2017 bull run, resulting in this graph:



Notice how the subsequest price action was completely underneath the projected curve fit line based on the data prior to the 2017 bull run.

----------

What now?

It's interesting to note how the historical curve fits using data prior to a bull run result in a projected line where the subsequent bull run price action lies below that projected line. In the case of the 2011 bull run, it's price action was almost all underneath the projected curve line. While in the cases of the 2013 and 2017 bull runs, their price actions were completely below the projected curve line.

It's almost as if the projected line was serving as an upper limit for the subsequent bull run's price action. The line doesn't give the actual prices at that point in time, rather it's indicating an upper limit for the price.

The question now is: does this historical pattern hold true for the present data? Does a curve fit using all data till the present result in a projected line where the next bull run's price action will remain below that line?

This is the curve fit applied to all data till the present:

Quote
General model Power2:
     f(x) = a*x^b+c
Coefficients (with 95% confidence bounds):
       a =      0.3132  (0.2636, 0.3627)
       b =      0.3707  (0.354, 0.3874)
       c =      -2.362  (-2.53, -2.194)

Goodness of fit:
  SSE: 394.7
  R-square: 0.93
  Adjusted R-square: 0.93
  RMSE: 0.3509

And this is the graph:



If, like what has happened in the previous bull runs, the next bull run's price action remains below that projected line then this would mean some interesting (sobering? depressing?) results:

- We will stay below 11,500 for the rest of 2019
- The earliest we can get back near 20,000 is around Dec 2020
- The earliest we can see 100,000 is around Mar 2024

I don't like these results because if we just take the last curve fit in isolation it offers a more optimistic outlook since the line looks like just an "average" of the price swing action, meaning we can go much higher above the line. But if we look at the performance of the historical curve fits, then it makes this latest curve fit line look like a price ceiling on the next bull run.
Jump to: