0
$\begingroup$

I am implementing a Random Forest classifier algorithm on Python for predicting future stock returns (one month). My goal is to foresee whether the cumulative returns in a month will be negative or positive and the magnitude of the movement. The label of the classification is:

  • -2 if the cumulative returns are negative and lower than a given threshold
  • -1 if the cumulative returns are negative but over the threshold
  • 1 if positive but lower than the threshold
  • 2 if positive and over the threshold

In doing so, I am using a list of features (predictors) taken from the literature:

  • Past $n$ returns
  • Some T-Bill rates
  • Financial and economical indicators such as Oil price, Gold price, treasury securities yield
  • Term and default spreads
  • Exchange rate
  • Returns on majour indices
  • Technical indicators: Volume, Volatility, Trend, Momentum

At the end I end up with more than 100 features and I apply a feature importance to select the best 20 features. However, both the in-sample and out-of-sample accuracy remain around 25% (as in the case of a random choice).

My question is whether there exist in literature better features or maybe strategies that may improve the predictive power of the model for the horizon I'm considering.

Improve this question
$\endgroup$
3
  • $\begingroup$ I am not sure if you are trying to predict monthly returns for individual stocks (N forecsasts every month) or for an index (such as the S&P 500) (one forecast every month). $\endgroup$
    – nbbo2
    Jun 14, 2020 at 15:28
  • $\begingroup$ I am trying to predict individual stock returns, so N forecasts every month (in particular now I am concentrating on ETFs but the model is built to be as general and flexible as possible). $\endgroup$
    – Matteo
    Jun 14, 2020 at 15:38
  • $\begingroup$ Binning like this does not make sense to me and can be highly problematic. It matters if you’re a cent below the threshold or a billion dollars below the threshold, yet you would regard those as the same. $\endgroup$
    – Dave
    Jan 1, 2022 at 4:27

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.