Last month I was asked to give a Conference talk on the subject of Data Science models so often failing to go live in production. After all, we have all come across “it works well on my machine” situations and we all have a general idea of why it’s often the case.
Many bloggers and commentators have provided thorough explanations of what leads a data science project to premature death, but here are my three favourites:
Using machine learning models to create targets for marketing campaigns is probably one of the tasks with the highest “looks good on my test set” / “oh, it didn’t work in the real world” ratio.
Let’s set the scene. You have been hired as a Data Scientist by a digital sweet shop company. Your task is to optimize marketing campaigns, specifically mailout or push notification campaigns where you typically award a coupon in exchange for buying a product. In a fictitious example, let’s say this is a fine Belgian Chocolate Box, with a 12$ margin. You offer a 10$ coupon…
Artificial Intelligence (A.I) is probably one of the most misused terms in technology and data science. If features in articles, books, politician speeches, hefty daily-rate consultancy companies PowerPoint slides. Even the Pope talks about it . As of 2019, according to Gartner, 1 out of 3 corporates claimed having implemented A.I. “in some form” .
But is Artificial Intelligence actually there?
Getting entangled in the controversy on what defines Human Intelligence is out of scope, however I will borrow some ideas from Judea Pearl and his Ladder of Causation . Pearl defines intelligence as a three steps process, with “learning…
I’ve worked for the past few years as a Data Scientist for mid-size to corporate companies. I enjoy solving problems with data and algorithms.