This is a toy project where we implemented a simple version of Linear regression to predict stock prices of three companies i.e Google, Microsoft and Amazon is done with accuracy of 74% with the training dataset of 200 days ranging from 19/3/2018 to 31/12/2018 and with a testing dataset of further 50 days.
Thus, the accuracy of the prediction model is constrained under the availabe training and testing datasets
This project uses the Linear Regression Algorithm for making the stock predictions. Further it uses the Gradient Descent Algorithm for optimization.
The predictions can be made for upto thirty days into the future.
Although the accuracy obtained from the current prediction model is moderately accurate, the accuracy can be further improved by using more advanced algorithms such as Support Vector Machine, Logistic Regression etc.
