Skip to content

Latest commit

 

History

History
35 lines (26 loc) · 1.33 KB

README.md

File metadata and controls

35 lines (26 loc) · 1.33 KB

Pharma_Stock_ML

In these tumultuous times a lot of people are asking the question can we look at the past and predict the future. We decided to take a swipe at the stock market, game stop anyone ?

Questions? Can we use machine learning to forecast the price of the stock looking at 10 years worth of historical prices ? Can we apply the same learning algorithm to a different sector ? Has 24/7 news dissemination and everyone analyzing the market overtaken good fundamentals?

With covid vaccines making an appearance we decided to choose pharmaceuticals as our sector to forecast prices. Stocks include Astrazeneca, Bristol Myers Squibb, J&J, Merck and Pfizer.

Refresh data daily using yahoo api.

Independent variables: Open, Close, Adjusted Close, High, Low and Volume

Dependent is forecasting price.

https://finance.yahoo.com/ Source: yfinance is the library

ML Algorithm: ARIMA auto regressive moving average model or fb profit.

Use plotly and javascript, be able to plot as the data changes.

Resources: https://www.analyticsvidhya.com/blog/2018/10/predicting-stock-price-machine-learningnd-deep-learning-techniques-python/

https://towardsdatascience.com/time-series-forecasting-predicting-stock-prices-using-an-arima-model-2e3b3080bd70

http://people.duke.edu/~rnau/411arim3.htm