Predicting stocks data - Rostlab/DM_CS_WS_2016-17 GitHub Wiki
- Proposer: Ishaan Raj -
@ishaanraj- [email protected] - Votes 🗳:
Summary
Predicting the financial data could result in high monetary returns. Many hedge funds are using ML tools to predict the stock price and create an exorbitant amount of profit. We can use Python libraries like Pandas to implement supervised regression learning on the stock's previous performance.
Data Set description
- Format: CSV
- Attributes: 7
- Rows: 4000(depending on stock listing date)
- Size: 40 MB
Our data set is in 3 profiles:Financial companies like Berkshire Hathaway, Goldman Sachs and Bank of America ; Crude oil based companies like Exxon Mobil,Chevron Corporation, Valero Energy; and Technology companies like Microsoft, Alphabet, HP. Further, we have brent crude oil and gold prices since 1970 to correlate with our stocks .
Attributes
- opening Date: which date is the information for?
- Open: the price that the stock opened at
- High: throughout the day,what was the highest price
- Low: throughout the day,what was the lowest price
- Close: the price stock closed at
- Volume: the amount of stock traded
- Adjusted Close: To adjust the price in case of stock split or dividend
Prediction goals
- Describe the stock history.
- Predict the stock.