LSTM Top Mistake In Price Movement Predictions For Trading

This is continuation of the previous video ( • Recurrent Neural Netwo... ) about LSTM or RNN neural networks common mistake or trap that is mostly advertised online for trading crypto, FOREX and stocks. Algorithms can be trained to assist traders but some results might be too good to be true and this video dives into one of the neural networks pitfalls. Price movement predictions are the ultimate purpose of these algorithms but they are not as easy to optimize for real life trading. Trading strategies are usually crafted and tested very carefully and any result looking too good should be doubted. I hope you will like this one, for the python code just follow the link to the previous video and the code is downloadable from the description.
Good luck for your trading and mostly for your algorithmic trading/learning!
🍓 Follow structured courses with more details and practice exercises check my "About" page for Discount Coupons on my Udemy courses covering:
- Python basics Kickstarter,
- Object Oriented Programming
- Data Analysis with NumPy and Pandas including financial analysis exercises,
... more courses are on the way drop me a message if you have a particular interesting topic!
Good luck!
#forexanalysis #neuralnetworks #deeplearning #trading #tradingbot #forex #stockmarket #stocktrading #stocktradingstrategies #algotrading #python
💲 Discount Coupon for My Udemy course on Algorithmic Trading:
bit.ly/CouponAlgorithmicTrading
The python code link:
drive.google.com/file/d/15xlg...

[@MasamuneX]

ive got a 6 gb csv file with the last 5000 days of price info for around 4800 companies merged with quarterly financial data like assets revenue etc merged with macro indicators like interest rates and all of that interpolated and cleaned up before passing to an lstm with many many layers with tuned hyper params. instead of using a standard loss value you should use mean absolute percentage error because if a stock is trading at 1$ and you have a loss of 1$ you would be off by 100% but if its trading at 1000$ and yoru loss is 10 then you would be off by 1%.

[@Mammel248]

The biggest pitfall of anyone starting with time series predictions (of any kind)! Predicting actual values instead of predicting the difference between values. Great video explaining why!

[@mj4ever001]

Great video, excellent observation about the good predictions phenomena, almost 90% of articles and papers i came across online show high accuracy, that is not applicable for the future only for test data, which is useless!

[@AntonAnisimovMSK]

Thank you very much for this video. I got the same result 6 months ago and did some experiments with the data. Now I have something like a 60-70% success rate when trading on 1st candles if the market is stable enough. The Binance BTC/FDUSD pair has seen a lot of volatility in recent days. 🙂

[@arashsadeghibablan2132]

You just saved me a LOT of time, thank you 🙏🏼❤️

[@camstuart]

That has really helped me! Straight to my notebooks for some experiments!!

[@truthforeman]

Great video! how would we modify this to predict multiple targets instead of one?

[@rebiiahmed7836]

Thank you a lot for your effort and the valuable content of this channel :)

[@bosypuspus]

For the bad predictions graph, I think it can be used as a golden crossover strategy between test and predicted prices

[@AshrafTheVoyager]

I tried your code for a few stocks and the results are amazing. Thank you

[@Rudaosong]

You are certainly right. I have traded cryptocurrency in practice for 3 months. I do the swing trading and clearly realize that it is hardly to calculate or predict the oscillate range of any coin. But I think trend prediction would be a better direction. Transferring the problem from regression to classification may be more efficient🧐

[@WishalSriRanganMU]

I Just got started with algo trading and I was wondering if using a LSTM model is really worth exploring due to this issue that has been brought up by you in this video. If not, do you have any suggestions on what model works best for forex trading in small timeframes such as 1min or 5 min charts? Great video by the way!

[@connectrRomania]

Good point bro, instead of predicting some precise values, we can build some models to predict for example trends or convergence based on the right indicators and still alot of preprocessing techniques must be applied to reach lets say some reasonable results.

[@elshadpiroghlanov7149]

Excellent explanation.

[@Andy-hs7ee]

I tried to do exactly the same 2 years ago and I gave up. Congrats for the achievement!!

[@kadourkadouri3505]

Nice ! But I sincerely think that data scaling is also a source of problems as most of the features are continuous (ATL, +inf). Therefore, usual scaling methods assume that the previous ATH will never be reached in the future in which case the model, no matter how sophisticated it is, will never predict a breakthrough (new ATHs).

[@BlackCatSyndicate]

Would love to see this built getting beginning to end and then modified and back tested.

[@eff.muhammad]

yes delayed prediction still a problem when using LSTM model, maybe prediction based on market sentiment is more useful

[@qwertasd7]

hm based upon avaraged indicators predict..>> Something slow moving, stears something wildly moving.. this might not be ideal engineering for LSTM use.

[@rezasadeghi2520]

thanks for the clarification - maybe worth removing the OHLC and add a lower EMA and then feed to the model? then the result may not be the same previous price?