Predicting Stock Prices

1 / 1

Predicting Stock Prices

In this project you need to demonstrates the future price prediction for different stocks using Recurrent Neural Networks.

Acknowledgements

This dataset for this project was obtained from the New York Stock Exchange dataset in Kaggle. You can find more about it from their competition page. You can find out more about the dataset from it's Kaggle page.

INSTRUCTIONS

You can find the data in the following path:

/cxldata/datasets/project/ny_stock_prediction

The dataset consists of 2 files, prices-split-adjusted.csv and fundamentals.csv. Here is a brief description of the content of the files:

prices-split-adjusted.csv: This file contains daily stock prices with added adjustments for splits. Most of data spans from 2010 to the end 2016, for companies new on stock market date range is shorter. There have been approx. 140 stock splits in that time, this set doesn't account for that.

fundamentals.csv: This file contains the metrics extracted from annual SEC 10K fillings (2012-2016), should be enough to derive most of popular fundamental indicators.

You can follow these steps to complete this project, however, you are free to test your own models:

  1. Read both the files and transform the data to pandas dataframe
  2. Extract all symbols from the list
  3. Extract a particular price for stock in symbols
  4. Normalize the data
  5. Create training set and test set
  6. Build the structure of model
  7. Train the model
  8. Denormalize the data
  9. Calculate the score

No hints are availble for this assesment

Answer is not availble for this assesment

Loading comments...