Stock Market Machine Learning

A machine learning model that makes use of Exponential Moving Averages (EMA's) to predict a future price of a stock. However, this model can and will be improved upon in the future as it will be converted to a Long Short Term Model (LSTM, a type of neural network) time series to maintain accuracy as the model predicts a greater number of steps into the future.

This project:

Uses a Kaggle dataset to analyze the data for thousands of different stock options

Makes use of MatPlotLib for data vizualizations

Implements both Exponential Moving Averages & Simple Moving Averages to predict a future stock price

Uses a test-train-split to train the first half of the data against the model, and then the other half to test it.

Returns a prediction for a future stock price.

Compares the accuracy of both the EMA & SMA through finding the Mean Square Error (MSE)

Technologies Used:

Python

TensorFlow

Neural Networks

Pandas

Numpy

Kaggle Stock Data

Sklearn

Simple Moving Averages

Exponential Moving Averages

Kaggle data used for this project: https://www.kaggle.com/borismarjanovic/price-volume-data-for-all-us-stocks-etfs Alphavantage link for API Key: https://www.alphavantage.co/support/#api-key