-1
$\begingroup$

Lately I was working on a LSTM code to predict future stock prices. I did not get a good result from that. Also I saw a lot of articles talking about stock market data is a random walk and cant be predicted by machine learning. I also know overfitting is the biggest problem in prediction but a technical analyst uses some stock indicators. I also feed them to my LSTM but still did not get good result. I don't understand how can we predict based on technical analysis but we can't do it with machine learning and NN.

$\endgroup$
1
  • 3
    $\begingroup$ I would challenge your assumption that you can predict stock prices using technical analysis $\endgroup$
    – Sammy
    Jan 20 at 11:38
1
$\begingroup$

This is likely due to overfitting, and it won't be easy to combat. If you would ask a skilled technical analyst you would notice that he is not using the same features you are inputting into the LSTM. Also, he has the capability of generalizing. If you would be able to feed the same input into an LSTM then maybe you could have similar results, but I would not expect you to be able to generalize the features to that level.

$\endgroup$
1
  • $\begingroup$ thanks for your answer. I know overfitting is the biggest problem in prediction but a technical analyst uses some stock indicators. I also feed them to my LSTM but still did not get good result. I guess I should try another model instead of LSTM but I have no idea what model can solve it $\endgroup$ Jan 20 at 15:35
0
$\begingroup$

It can be due to several reasons at once:

  • Underfitting or overfitting your model. It is clear, I think.
  • You try to forecast data for a long period of time. Financial data tends to change its behaviour from time to time, hence only short-term forecasting is suitable. Moreover, financial date depends not only on previous values, but on some other external factors. Using technical analysis you is able to predict trend movements, but not exact price values. There are several articles on arXiv.org about stocks forecasting that proves this point of view.
$\endgroup$
2
  • $\begingroup$ Thanks for your contribution. There are lots of people that only use technical analysis without any fundamental analysis and still get a good result using only stock indicators. Anyway I approve your idea that short-term forcasting (almost realtime with dataframe like 30mins ) is better than long-term forcasting $\endgroup$ Jan 20 at 15:45
  • $\begingroup$ @mohammadagah, yeah, that's true. But when using technical indicators, a lot of heuristics are applied too. Technical indicators help to generate buy/sell signals based on some combination of its values, prices and other data (e.g. volume). They are not targeted to predict exact future value of price, some of them (mainly trend-based) estimate future trend movements, but nothing more. But if you know some researches about predicting prices with past data and indicators values (possible collinearity here? Indicator values depend on prices...), please share it with me :) $\endgroup$ Jan 22 at 22:26

Not the answer you're looking for? Browse other questions tagged or ask your own question.