The Oracle, predict the stock market ?

The Oracle logo


The Oracle is a Python library that uses several AI prediction models to predict stocks returns over a defined period of time.

It was firstly introduced in one of my previous package called Empyrial.

Disclaimer: Information is provided ‘as is’ and solely for informational purposes, not for trading purposes or advice.

How to install ?

pip install the-oracle

How to use ?

from the_oracle import oracle
      portfolio=["TSLA", "AAPL", "NVDA", "NFLX"], #stocks you want to predict
      start_date = "2020-01-01", #date from which it will take data to predict
      weights = [0.3, 0.2, 0.3, 0.2], #allocate 30% to TSLA and 20% to AAPL...(equal weighting  by default)
      prediction_days=30 #number of days you want to predict


The Oracle output

About Accuracy

MAPE Interpretation
<10 Highly accurate forecasting ?
10-20 Good forecasting ?
20-50 Reasonable forecasting ?
>50 Inaccurate forecasting ?

Models available

Models Availability
Exponential Smoothing
Facebook Prophet
4 Theta
Fast Fourier Transform (FFT)
Naive Drift
Naive Mean
Naive Seasonal

Stargazers over time


Contribution and Issues

The Oracle uses GitHub to host its source code. Learn more about the Github flow.

For larger changes (e.g., new feature request, large refactoring), please open an issue to discuss first.

Smaller improvements (e.g., document improvements, bugfixes) can be handled by the Pull Request process of GitHub: pull requests.

  • To contribute to the code, you will need to do the following:

  • Fork The Oracle – Click the Fork button at the upper right corner of this page.

  • Clone your own fork. E.g., git clone
    If your fork is out of date, then will you need to manually sync your fork: Synchronization method

  • Create a Pull Request using your fork as the compare head repository.

You contributions will be reviewed, potentially modified, and hopefully merged into the Oracle.

Contributions of any kind are welcome!



You are welcome to contact us by email at [email protected] or in Empyrial’s discussion space




View Github