In Excel look at stocks.csv
1) Before analyzing the file, what do you think is the largest indicator to predict ‘Tomorrow’s Percent Change’? Purely your opinion, try to form some intuition on features.
Load the Data with pandas and analyze the correlation
2) Were there any strong indicators (positive or negative)?
3) What in the data is missing that might be a stronger indicator from your own knowledge of stocks?
4) Come up with one new feature based off the current data that gives a stronger (positive or negative) correlation than the existing values (stronger just means slightly higher positive or slightly lower negative correlation)
Submit your python code and answers to the 4 questions