Skip to content

forecasting the price of MSFT stocks by classical and RNN time series methods

Notifications You must be signed in to change notification settings

Olhaau/stock_price_prediction

Repository files navigation

Predicting stock prices

Project overview

  • In this project I wanted to forecast stock prices using the time series prediction methods (ARIMA, LSTM) from my weather forecast project
  • Microsoft closing stock prices are used as example
  • TODO: the goal is a tool that gathers most recent stock market data and make accurate forecasts

Calculated results of a LSTM forecast

stock_prediction

with the following accuracy in the predictions:

MAPE RMSE
0.72% 1.39

Calculated results of a ARIMA forecast

ARIMA_stock_pred

with the following accuracy in the predictions:

MAPE RMSE
6.33% 13.46

Some good descriptions on stock market prediction

Overview of usable methods

Also:
https://www.kaggle.com/pablocastilla/predict-stock-prices-with-lstm
https://towardsdatascience.com/predicting-stock-price-with-lstm-13af86a74944

About

forecasting the price of MSFT stocks by classical and RNN time series methods

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published