+- Hack Forums (https://hackforums.net)
+-- Forum: Money (https://hackforums.net/forumdisplay.php?fid=241)
+--- Forum: Crypto Currency (https://hackforums.net/forumdisplay.php?fid=380)
+--- Thread: My predictions for Bitcoin for the next 4 days (/showthread.php?tid=6162860)
My predictions for Bitcoin for the next 4 days - SIM-3867235 - Jul 10, 2021
Hello everyone, I am testing out my Keras model for Bitcoin price forecasting. These are my current predictions. Not financial advice.
2021-07-10 to 2021-07-11 Market direction: DOWN
2021-07-11 to 2021-07-12 Market direction UP
2021-07-12 to 2021-07-13 Market direction DOWN
Let's see if they are accurate! :)
RE: My predictions for Bitcoin for the next 4 days - Fountain Of Youth - Jul 10, 2021
Smart people are buying the dips
RE: My predictions for Bitcoin for the next 4 days - SA777OSHI - Jul 10, 2021
Market is so boring that people is making threads of price predictions for a range of 2k,
Nevermind now you edited the thread and it only shows the direction it will go for the next 3 days without price prediction? Ok
RE: My predictions for Bitcoin for the next 4 days - Recon12345 - Jul 10, 2021
Did ya get your crystal ball from Costco?
RE: My predictions for Bitcoin for the next 4 days - .Infinity. - Jul 10, 2021
Wow, you expect it to go down, and then up, and then down? That's insane bro you should start a group.
RE: My predictions for Bitcoin for the next 4 days - m8than - Jul 10, 2021
now train your keras model on weekly basiss
RE: My predictions for Bitcoin for the next 4 days - SIM-3867235 - Jul 11, 2021
(Jul 10, 2021 12:18 PM)SA777OSHI Wrote: Market is so boring that people is making threads of price predictions for a range of 2k,
Nevermind now you edited the thread and it only shows the direction it will go for the next 3 days without price prediction? Ok
That's not what I'm out for. I engage in a lot of futures high-leverage trading where knowing price movements in a 2k range results in a higher change of making a good trade.
(Jul 10, 2021 07:31 PM)m8than Wrote: now train your keras model on weekly basiss
That is the idea :)
(Jul 10, 2021 07:27 PM).Infinity. Wrote: Wow, you expect it to go down, and then up, and then down? That's insane bro you should start a group.
LOL, its about knowing when the market changes direction that is important.
RE: My predictions for Bitcoin for the next 4 days - T0Bi - Jul 11, 2021
(Jul 11, 2021 08:20 AM)waytoosplashy Wrote: That's not what I'm out for. I engage in a lot of futures high-leverage trading where knowing price movements in a 2k range results in a higher change of making a good trade.
That is the idea :)
LOL, its about knowing when the market changes direction that is important.
Why did you remove your price targets?
RE: My predictions for Bitcoin for the next 4 days - shreder - Jul 11, 2021
7-10 and 7-11 market up rip lets see next one
RE: My predictions for Bitcoin for the next 4 days - SIM-3867235 - Jul 11, 2021
(Jul 11, 2021 09:29 AM)shreder Wrote: 7-10 and 7-11 market up rip lets see next one
![[Image: 2e2b9e3b3cf8ef3710aa83fb4805053b.png]](https://i.gyazo.com/2e2b9e3b3cf8ef3710aa83fb4805053b.png)
So far on the 1hr chart the predictions have been correct.
(Jul 11, 2021 09:16 AM)T0Bi Wrote: Why did you remove your price targets?
Because my model is still very unstable and after three more consecutive tests after posting I got different values but same market directions. Which so far, tells me that market direction is the most accurate.
RE: My predictions for Bitcoin for the next 4 days - Blue Eye Samurai - Jul 11, 2021
What am I even looking at.
RE: My predictions for Bitcoin for the next 4 days - m8than - Jul 11, 2021
(Jul 11, 2021 02:47 PM)waytoosplashy Wrote:
So far on the 1hr chart the predictions have been correct.
Because my model is still very unstable and after three more consecutive tests after posting I got different values but same market directions. Which so far, tells me that market direction is the most accurate.
This is called confirmation bias. Your model is probably correct by mostly luck but you want to believe it actually works even though it doesn't work for the task you set it (predicting prices)
RE: My predictions for Bitcoin for the next 4 days - SIM-3867235 - Jul 12, 2021
(Jul 11, 2021 09:55 PM)m8than Wrote: This is called confirmation bias. Your model is probably correct by mostly luck but you want to believe it actually works even though it doesn't work for the task you set it (predicting prices)
No this is called LSTM Time-series machine learning where a computer learns to predict point in a time-series sequence like price movement. I have revised the model and will add new predictions soon.
(Jul 11, 2021 09:55 PM)m8than Wrote: This is called confirmation bias. Your model is probably correct by mostly luck but you want to believe it actually works even though it doesn't work for the task you set it (predicting prices)
The model results in a 60% accuracy of replicating bitcoin movement. You dont 'believe' anything when training a model. You train it and look at the results.
Update
The original predictions were:
2021-07-10 to 2021-07-11 Market direction: DOWN
2021-07-11 to 2021-07-12 Market direction UP
2021-07-12 to 2021-07-13 Market direction DOWN
Between 2021-07-10 and 2021-07-11 the market dropped 3.7%.
Between 2021-07-11 and 2021-07-12 the market went 3.6% bullish.
Between 2021-07-12 and creation of post the market is down 4.9%.
In conclusion the model has been able to predict market direction but there is still uncertainty whether this was a coincidence or not.
New Predictions
2021-07-13 to 2021-07-14 DOWN
2021-07-14 to 2021-07-15 UP
RE: My predictions for Bitcoin for the next 4 days - m8than - Jul 12, 2021
(Jul 12, 2021 03:33 AM)waytoosplashy Wrote: No this is called LSTM Time-series machine learning where a computer learns to predict point in a time-series sequence like price movement. I have revised the model and will add new predictions soon.
I know what it's called. I'm telling you what your brain is doing lol
RE: My predictions for Bitcoin for the next 4 days - SIM-3867235 - Jul 12, 2021
(Jul 12, 2021 05:18 PM)m8than Wrote: I know what it's called. I'm telling you what your brain is doing lol
Its not confirmation bias when the predictions represented the majority of the market movements.
(Jul 12, 2021 05:33 PM)Focus Broken Wrote: Well done! To compare this with coincidence, the chance of guessing this outcome correctly at random is 12.5%.
Thanks man, I’ve been working on this since August 2020. Even though the model’s simulated accuracy is high, real world accuracy tends to decrease. I will be doing this for a couple of weeks until it would be profitable to invest in accordance to predictions.