Hey there. I found that regression models do okay when the feature-set is simple. And I can see that deep learning seems like overkill but I found that it can create models that does justice to the complexity of real estate.
Hey Arubis, you're absolutely right. I copied the model from Scott (even the domain name). I'm unabashedly a huge fan and early subscriber of his newsletter since mid-2014.
You're right, I updated it to reflect that it's paid. I think email address is implied by the newsletter though.
I'm obviously biased but I think the problems are fun and the solutions are valuable. Here are some blog posts I wrote that hopefully give you an idea of our questions:
I run a (paid) newsletter that sends fun coding interview puzzles every day. If you're interviewing around (or if you just enjoy programming problems), check out Daily Coding Problem: https://dailycodingproblem.com/!
I'm working on better automation and alerts for my newsletter, Daily Coding Problem (https://dailycodingproblem.com/). Specifically, I set up a bot on Slack and now I want it to message each day's stats (emails sent, open rate, click rate) as well as notify on events (subscribe/unsubscribe, email).
I created Juicebox, which lets you listen to youtube/soundcloud songs with other people: https://www.juicebox.dj/
I have made no money off of this. In fact, I've probably paid hundreds in hosting/domain fees. But I love what I've built so far and use it everyday with my friends. Please check it out, I'd love to hear any feedback!