I enjoy giving talks and workshops on Data Analytics. Here is a list of some of the talks I’ve given. In my Mathematics master I regularly gave talks on technical topics, and previously I worked as a Teacher in a School in Northern Ireland. I consider the evangelism of data and analytics to be an important part of my job as a professional analyst!

**Slides and Videos from Past Events**

PyCon Ireland – From the Lab to the Factory – I gave a talk on the business side of delivering data products – a trope I used was it is like ‘going from the lab to the factory’. This was a well-received talk based on the feedback and I gave my audience a collection of tools they could use to solve these challenges.

EuroSciPy 2015: I gave a talk on Probabilistic Programming applied to Sports Analytics – slides are here.

My PyData London tutorial was an extended version of the above talk – but will be more hands-on than the talk version.

I spoke at **PyData** in Berlin.

The link is here

The blurb for my upcoming PyData Berlin talk is mentioned here.

**Abstract:** “Probabilistic Programming and Bayesian Methods are called by some a new paradigm. There are numerous interesting applications such as to Quantitative Finance.

I’ll discuss what probabilistic programming is, why should you care and how to use PyMC and PyMC3 from Python to implement these methods. I’ll be applying these methods to studying the problem of ‘rugby sports analytics’ particularly how to model the winning team in the recent Six Nations in Rugby. I will discuss the framework and how I was able to quickly and easily produce an innovative and powerful model as a non-expert.”

In May 2015 I gave a preview of my PyData Talk in Berlin at the Data Science Meetup on ‘Probabilistic Programming and Rugby Analytics‘ – where I presented a case study and introduction to Bayesian Statistics to a technical audience. My case study was the problem of ‘how to predict the winner of the Six Nations’. I used the PyMC library in Python to build up statistical models as part of the Probabilistic Programming paradigm. This was based on my popular Blog Post which I later submitted to the acclaimed open source textbook Probabilistic Programming and Bayesian Methods for Hackers. I gave this talk using an IPython notebook, which proved to be a great method for presenting this technical material.

In October 2014 I gave a talk at Impactory in Luxembourg – a co-working space and Tech Accelerator. This was an introductory talk to a business audience about ‘Data Science and your business‘. I talked about my experience at different small firms, and large firms and the opportunities for Data Science in various industries.

In October 2014 I also gave a talk at the Data Science Meetup in Luxembourg. This was on ‘Data Science Models in Production‘ discussing my work with a small company on developing a mathematical modelling engine that was the backbone of a ‘data product’. This talk was highly successful and I gave a version of this talk at PyCon in Florence in April 2015. The aim of this talk was to explain what a ‘data product’ was, and discuss some of the challenges of getting data science models into production code. I also talked about the tool choices I made in my own case study. It was well-received, high level and got a great response from the audience. Edit: Those interested can see my video here, it was a really interesting talk to give, and the questions were fascinating.

When I was a freelance consultant in the Benelux I gave a private 5 minute talk on Data Science in the Game industry. Here are the slides. – This is from July 2014

My Mathematical research and talks as a Masters student are all here. I specialized in Statistics and Concentration of Measure. It was from this research that I became interested in Machine Learning and Bayesian Models.

**Thesis**

My Masters Thesis on ‘Concentration Inequalities and some applications to Statistical Learning Theory‘ is an introduction to the world of Concentration of Measure, VC Theory and I used this to apply to understanding the generalization error of Econometric Forecasting Models.