Forecasting My Medium Followers growth using machine learning

Photo by Isaac Smith on Unsplash

Introduction

I spend quite some time and efforts in increasing my followers on various platforms like LinkedIn, Twitter, Medium, YouTube. As a data scientist, I am constantly analyzing my numbers to determine which platform offers the greatest potential for growth in comparison to the amount of effort required to build the audience.

In this article I will demonstrate how I have used machine learning to learn from historical followers data provided by Medium to forecast the growth over next 2 years.

I have used PyCaret’s Time Series Module for this tutorial. The Google Colab Notebook I have used for the experiment is available here.

PyCaret

PyCaret is an open-source, low-code machine learning library in Python that automates machine learning workflows. It is an end-to-end machine learning and model management tool that speeds up the experiment cycle exponentially and makes you more productive.

To install the PyCaret library in Python using pip:

# install pycaret 3.0-rc
pip install --pre pycaret

Dataset

In order to estimate the growth, we require historical data of our Followers. To get this information, navigate to the…