How do you teach an algorithm what a good .com domain is?

𝐓𝐋𝐃𝐑; I trained a LinearSVC to predict good .com domains with 0.74 accuracy.

See for yourself how the model performs in action at https://DailyDomainIdeas.com or @DomainIdeaDaily on Twitter, or feel free to read the medium post for more details on the process I used.

𝐋𝐨𝐨𝐤𝐢𝐧𝐠 𝐟𝐨𝐫 𝐲𝐨𝐮𝐫 𝐧𝐞𝐱𝐭 𝐛𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐢𝐝𝐞𝐚 𝐨𝐫 𝐚 𝐧𝐞𝐰 𝐬𝐢𝐝𝐞 𝐩𝐫𝐨𝐣𝐞𝐜𝐭?

I love product ideas (shiny object syndrome), and I'm coming up with new ideas almost daily.

So 1 month ago, I decided to daily publish 𝐞𝐯𝐞𝐫𝐲 single idea that popped up as a side project.

As I started to publish all the domain ideas, I thought that "this would definitely be possible to automate with machine learning."

So I did.