Investors typically seek to profit from a stock by buying low and selling high. To achieve this, an investor must purchase the stock at the right price. Predicting stock prices is not an exact science, but figuring out the mechanism behind some macroeconomic features can help the stakeholders make the right descision. We investigated various machine learning models to predict stock market price.
Our data is scrapped from several main platforms, such as S&P 500, Russel 2000 etc. Some experiemented models includes random forest, ARIMA, facebook prophet from the pure time sequential perspective. Later we are seeking to improve available models' prediction by adding macroeconomic features. Finally, we report our results in the methodlogy section, and interpret it to give some actionable insights for stakeholders.