How to Build a Simple Stock Movement Classifier Using Machine Learning

We harness computing power and machine learning to build a classifier tool to predict whether a stock will go up or down on any given day. It helps investment managers boost their predicting power in their investment management practices.

Introduction

Since the advent of financial markets, humankind has been trying to predict the market and to have market psychology work in their favor. As technology is getting more and more advanced, we have the unprecedented computational power to uncover hidden patterns in financial data that eluded traders up until today. The purpose of this project is to harness this computing power by building a machine learning-powered classifier to predict whether a stock will go up or down on any given day. This is particularly useful for investment managers so that they can have better predicting power in their investment management practices.

We shall attempt to answer the following questions as a first step towards our journey to create trading strategies using the latest artificial intelligence/machine learning and data science tools:

• Can historical price and volume data serve as potential features to predict the respective stock prices?
• Does the overall historical stock market volatility have any correlation with the price data of a given stock and can it be used as a feature as well?
• Can we use supervised ML classifier models to predict whether the stock price will go up or down on any given day?