Introducing Observable, self-documenting ELT
Cross posting to original article posted here View at Medium.com
sane.a.lytics
finding meaning in data
Latest posts
How I scaled Machine Learning to a Billion dollars: Strategy
Cross posting here to original article I posted in https://medium.com/@analyticsaurabh/how-i-scaled-machine-learning-to-a-billion-dollars-strategy-2379faf86c02
Live Blog – day 4,5 – Dress recommendation models
<Please note that this post is unfinished because ************ even though we delivered better than expected results! Unlimited program went on to be 70% of revenue during my tenure> This post is probably what you expected this series to be. Previously, on building a production grade state of the art recommendation system in 30 days: […]
Live Reco build days 2-3 – Unlimited recommendation models
This is second post in the series started here. The goal of this experiment is to help new data scientists see how things are really built outside textbooks and kaggle. Also, if you want to work on challenging real world problems (not ads), come work with us. The previous post covered proposals with Engineering because […]
Live blogging building a production recommendation engine in 30 days
Vanity We are all guilty of it. Every tech team wants to show off their stack as this big beautiful Ferrari they are proud of. What they often omit is what is glued together by duct tape and 20 other cars they built without engines. I think this is disparaging to new data scientists. Creating […]
Dreaming up new dresses via AI and game theory
Level: Beginner, circa 2014 Or I can haz fashion. Here are some pretty pictures to motivate you These are all ‘dreamt’ by a neural net. OK, now for the old bait and switch. Let’s talk Deep Learning for a second. For the uninitiated, traditional machine learning works something like this. Say you are trying to […]
Human in A.I. loop
Practical example of how to leverage humans and artificial intelligence strengths at a fashion company.
Matrix factorization
Or fancy words that mean very simple things. At the heart of most data mining, we are trying to represent complex things in a simple way. The simpler you can explain the phenomenon, the better you understand. It’s a little zen – compression is the same as understanding. Warning: Some math ahead.. but stick with it, it’s worth […]
Testing recommender systems in R
Recommender systems are pervasive. You have encountered them while buying a book on barnesandnoble, renting a movie on Netflix, listening to music on Pandora, to finding the bar visit (FourSquare). Saar for Revolution Analytics, had demonstrated how to get started with some techniques for R here. We will build some using Michael Hahsler’s excellent package […]