Using Machine Learning to predict sales during the quarantine restrictions — Part 1
This post started with the idea of being one post covering a hypothesis I had and explored to predict my family’s restaurant business sales with minimal data and the usage of machine learning. When I started writing, it became apparent to me that it will be a long post.
For this reason, I have decided to split it into two parts. The first one is exploring some of the ideas and theories that we need to understand before we dive into the logic I used to build the model. The second one will explore the model itself.
Without further ado let’s get into it.
This is not going to be a coding step by step post because the data I worked with is from an actual business.
I would love to go through the numbers, but I hope you understand that a business’ numbers are not for everyone to see. Instead, I will try to convey the story using story-telling and some graphs (without the y-axis).
With that out of the way, let’s begin.
Business Case
My parents own AINA, a small restaurant in Stirling, Scotland, UK. They opened the business in August of 2018 (almost two years at the time of writing this post).