How I Built My Own Real-Time Parking Availability Predictive Model

A simple way of using machine learning to help me in my everyday life.

Photo by Sven Mieke on Unsplash

In this day and age, machine learning (ML) is widely applied in almost every industry, tackling some of the most complex challenges. It is used in medical diagnosis of illnesses, detection of fraud, self-driving cars, facial recognition, recommendation systems etc. In most applications, the use of ML produces large-scale impact and benefits the masses.

But, does it always have to be that way? Can we keep things small-scale and use ML in our own little ways, in our everyday lives? Of course! In this post, I write about a self-initiated project where I did just that — using ML to predict parking space availability at my residential premise.

p.s. Feel free to check out the source code for this project at this GitHub repo.

Table of Contents

1. Problem statement
2. Data collection
3. Feature engineering
4. Exploratory data analysis
5. Building a baseline model
6. Creating a web app with Streamlit
7. Wrapping it up

Problem statement