On Tuesday I spoke at CRAP Talks MCR. CRAP is a snappily titled meetup about ‘Conversion Rate, Analytics and Product’. There was a range of people in attendance mostly working either in e-commerce or digital agencies. I’d been once before and I liked the range of topics and mix of people there: a bit off my usual machine learning and data science beat.
There first talk was a really interesting one about Intelligent Tracking Protection (ITP) and its impacts on the internet by Liam Galliers from Code Computerlove. For those who haven’t heard of this (like me), it is an attempt to stop excessively intrusive tracking by Apple and webkit, and is part of a battle between various internet giants (apple vs facebook and google) for the future of the internet. ITP is going to make quite a big impact on attempts to improve websites through things like A/B testing, at least for the 13% or so who use the safari browser.
The last talk was about CRAP at Matalan by Jack Osborne. A really good overview of how digital analytics can lie at the centre of an organisation. For me, as a bit of an outsider, this was useful for seeing how these things work in an organisation.
Thanks to Becky Lacock for organising a great event.
My talk was a slightly updated version of the machine learning 101 talk I’ve given a couple of times. I stripped it back a bit and added some animated gifs to illustrate how a simple linear model gets trained. The audio and slides are below. After the talk, somebody asked about good resources for learning about machine learning for the beginner. Here are a few:
- Prediction Machines by economists Ajay Agrawal, Joshua Gans and Avi Goldfarb. I liked this books non sensationalist and fairly accurate portrayal of how machine learning can be used in business
- Hello World: How to be Human in the Age of the Machine by Hannah Fry. I haven’t actually read this book yet, but I really like Hannah Fry and the blurb and extracts seem good.
- A slightly bigger time commitment is Andrew Ng’s hugely popular online machine learning course.
- Another, fairly technical book, that I like is An Introduction to Statistical Learning
If you have any more suggestions please leave them in the comments below.
Here is an audio recording of the talk.
Here are the slides.