Prophecy

Inspiration

I recently learned Python and one of its most powerful applications, machine learning. I am also interested in investing in the stock market and wanted to connect these two passions.

What it does

Prophecy uses the opening price of a ticker symbol along with historical data to make an accurate prediction about the closing price of that stock.

How I built it

I built Prophecy using data from Yahoo Finance and an XGBoost Regression model. I created the predictor with several other models such as a Random Forest Regression model and found the XGBoost Regression model to make the most accurate predictions.

Challenges I ran into

I faced difficulties in formatting the historical data to use in the model as well as creating different models to compare.

Accomplishments that I'm proud of

I am really proud of this project and the success it has. As the stock market is closed on the weekends, I provided the model with the opening price of Apple's stock on March 26th, 2021 which was $120.39. The model predicted that Apple would close at $120.68 and Apple actually closed at $121.21.

What I learned

I learned how to create several different machine learning models as well as how to make predictions using those models. I also learned how to read and format data using Pandas and how to perform calculations using NumPy.

What's next for Prophecy

In the future, I hope to improve Prophecy to make predictions for longer periods of time. Currently, the model can make accurate predictions for the daily price of a stock. I intend on improving the model to accurately predict the value of a stock after a week or even a month.

Built With

• numpy
• pandas
• python
• sklearn
• xgboost