Disclaimer: Market and Machine Learning

Stocks are definitely a time series. As is any data with a consecutive time point for each value. Unfortunately, you can’t reliably beat the market.

“Deep Learning with Python” Book by Chollet says, Markets have very different statistical characteristics than natural phenomena such as weather patterns. Trying to use machine learning to beat markets, when you only have access to publicly available data, is a difficult endeavor, and you’re likely to waste your time and resources with nothing to show for it.

_Always remember that when it comes to markets, past performance is not a good predictor of future returns — __looking in the rear-view mirror is a bad way to drive. _Machine learning, on the other hand, is applicable to datasets where the past is a good predictor of the future.

Using Time Series Predictions to predict stock prices and make us all rich is a very bad idea Instead, it can make us a loss in millions if we blindly depend on it.

Introduction

This post is about learning about Facebook’s Prophet and using it to predict the S&P 500 as a tutorial.

In this tutorial, we will forecast stock prices using Prophet (Facebook’s library for time series forecasting). However, historical prices are no indication of whether a price will go up or down. I’ll rather use my own variables ( Moving Average’s ) and use machine learning for stock price prediction rather than just using historical prices as an indication of a stock price increase.

What is Facebook’s Prophet?

The most commonly used models for forecasting predictions are the autoregressive models. Forecasting can be hard science and requires substantial expertise. So In an attempt to develop a model that could capture seasonality in time-series data, Facebook’s Research Team developed and open-sourced Prophet, which allows anyone with Python or R programming skills to implement forecasts on time series easily.

#stock-market #time-series-forecasting #python #machine-learning #prophet