@zendatastudio
Additional things to try: 1. Define a quality score: calculated as how closely the trendline matches the highs and lows (this rules out sudden price change and pave way for dynamic trend lines) 2. Dynamic trend line: set a range of periods (7-30), calculate trend line for each period but only select one with best quality score (We can call it true trend line).
@rverm1000
Nice just shows I got along way to go to get better at programming
@zeref4727
I also did gradient descent but i used the positive data from the y-y_pred for resistance and negative for support
@poisonza
computationally too expensive, the gradient descent part could go away. Given data window compute zigzag to find pivot points Enumerate all possible trend line using pivoot points. choose trend line with minimum error(distance between data and trendline). So essentially you compute way less but get similar result. cheers
@张海墨
thank you sir ! this is really nice!:medal-yellow-first-red:
@LongTu167
Amazing, thank you very much!!!
@parklife6384
Thanks for your videos, they are very informative and well explained.
@bradley1995
Id have it add more time periods to calculate if it detects it is continuing in the same trend.
@GaryBernstein
can you share the C/C++ code?
@DeAdBiGeYeFiSh
I think that a simpler way (in terms of steps of calculations) performs better in terms of computational complexity. For the bottom line: Start with a line joining the pivot point (or starting point) with the next point of close/low. Then go on checking the next points one by one. If the next is above the line, just pass. Otherwise, switch the line with the line joining the starting pivot point with this new point. By the end you have the desired trend line. I find your steps more conceptually appealing though, the people who would probably disagree would be CS heads that tend to prefer faster iterative/recursive algorithms.
@SataMoore
I am wondering how to ensure k bars within the tread channel as shown in the presentation, since with MSE the fitted data (the low values in the support mode for instance) must scatter along the trendline.
@ponkieponkz
I dont understand how the pivot is calculated or stored in the dataframe... ***Never mind... Newbie here. I started learning python in april this year. I am retrofitting your codde to a Freqtrade dataframe. You are working with numpy arrays. Learned some new stuff thanks to this challeng.. Thanks for the content.
@iomatrix2
What software is getting used to visualize the trendline in the video?
@probablyonthemoon
Howdy Brother, love your work! Was wondering, do you log-transform price data before testing? Crypto prices can be very YEEHAW exponential
@brendanlydon5272
Would you consider the normal equation instead of GD if n < 10^4? Unreal content btw. Would love to see a video on a long/short strategy with a neural net and playing with many feature variables predicting X candles ahead. Distance to vwap, 2nd stddev bollinger bands, maybe distance to top/bottom trend lines in current trend?
@nattyzaddy6555
I ran your code but it created a static matplotlib graph instead of the real-time updated graph that you show in the video
@cwayne4
I think i found a faster way. Compute Line of best fit. Compute the diffs of the line and the closing prices. Get the maximum diff of the first half of the line, thats your first pivot. Get the maximum diff of the second half of the the line, thats your second pivot. The trendline then can be calculated with the two pivots. Except for the fitting of the line all other operations are just lookups. Or am I missing something?
@Mega-wt9do
i made a version that uses a better method than the gradient descent that computes it directly and it can compute the trend lines about 27000 times a second inside of turbowarp (a compiled version of scratch)
@DaniilOkladnikov-b2h
Doesn't your algorithm find the line that goes through lowest low and has biggest slope while being under all data points? You don't need to do gradient descent search if so.
@acedusse5119