Using Machine Learning to Replicate Airbnb's Amenity Detection Part 2: Data Exploration

I read an article the other which described how Airbnb uses computer vision and machine learning to automatically detect amenities (household objects) in their listings. I loved it so much I decided to replicate it in my own version as a machine learning project.

Over the next six weeks (42 days), I’ll be replicating/improving their pipeline and documenting it as I go. This video describes the project overview. As I get further along, there will be more going through each step of the process.

Note: I am not affiliated with Airbnb nor are they involved with this series of videos in any way.

0:15 – Article which inspired this project
1:00 – Whiteboard planning
1:43 – Model we’re going to use
2:01 – Workspace explanation (Google’s Deep Learning VM)
3:35 – Project criteria
4:37 – Dataset we’re going to be using (Open Images)
7:32 – How a machine learning project starts
8:58 – Exploring Open Images
10:22 – Script we’re using for downloading images
11:27 – First data roadblock
13:45 – Wrap up and next steps

All videos in this series:
Full playlist –
Part 1 (overview) –
Part 2 (data exploration) –
Part 3 (data manipulation) –
Part 4 (building a small dog model) –
Part 5 (experiment tracking) –
Part 6 (modelling experimentation) –
Part 7 (building a big dog model) –
Part 8 (getting my modelling deployed) –
Part 9 (project wrap up and retrospective) –

My machine learning course –
All of my notes/ideas in Notion –
Airbnb Amenity Detection article –
Script for downloading Open Images –

Get email updates on my work –
Support on Patreon –

Connect elsewhere:
Web –
Quora –
Medium –
Twitter –
LinkedIn –

#machinelearning #datascience

Source of this AI Video

AI video(s) you might be interested in …