Dom Di Francesco, PhD, CEng

thoughts on risk, uncertainty, statistics and decisions

Recent Posts

All Posts

advent of code 2025
Julia
puzzles
Advent of code is a website created by Eric Wastl, releasing a (increasingly challenging) programming puzzle each day. This year we will not be receiving the usual 25 days…
Domenic Di Francesco
Dec 8, 2025

diff all the things
automatic differentiation
deep learning
Bayesian inference
Julia
Enzyme
Gradients guide us through high-dimensional parameter space to draw samples from posterior distributions, take steps towards loss minimising parameter values, identify model…
Domenic Di Francesco
Sep 9, 2025

The Turing Podcast
podcast
Bayes
engineering
dogs
Last year, I participated in an episode of the Alan Turing Institute’s Coffee Pod podcast. It was hosted by my friend Bea and we talked about my background in engineering…
Domenic Di Francesco
Jan 25, 2024

Who Am I?
football
R
Shiny
At a previous job, my colleagues and I would occasionally create football (soccer) quizzes for each other. The game I used to send them would involve me sequentially sending…
Domenic Di Francesco
Mar 21, 2023

Bayes@Lund2023
Bayes
Stan
Julia
decisions
value of information
A recording of my presentation on value of information analysis at the Bayes@Lund2023 conference.
Domenic Di Francesco
Jan 23, 2023
 
All Your Bayes 2.0
news
I’ve recreated this site in quarto, and plan on writing more jargon-free articles on risk, uncertainty, decisions, statistics, and football.
Jan 23, 2023

Player Form. Part 1
football
analysis
Stan
uncertainty
Bayes
gaussian process
When is a player in form (over performing, or enjoying a hot streak) and how long does this last? If there is such an effect, I suspect it will be a result of some…
Domenic Di Francesco
Jan 19, 2023

Uncertainty in xG. Part 2
football
analysis
xg
Stan
uncertainty
Bayes
multi-level modelling
partial pooling
This is part 2 of an article on fitting a Bayesian partial pooling model to predict expected goals. It has the benefits of (a) quantifying aleatory and epistemic uncertainty…
Domenic Di Francesco
Jan 7, 2021

Uncertainty in xG. Part 1
football
analysis
xg
Stan
uncertainty
Bayes
multi-level modelling
partial pooling
The Expected Goals (xG) metric is now widely recognised as numerical measure of the quality of a goal scoring opportunity in a football (soccer) match. In this article we…
Domenic Di Francesco
Dec 10, 2020

Why be Bayesian?
Bayes
uncertainty
decisions
This post is intended to be a high-level discussion of the merits and challenges of applied Bayesian statistics. It is intended to help the reader answer: Is it worth me…
Domenic Di Francesco
Mar 24, 2020

Bayesian Logistic Regression with Stan
Bayes
logistic regression
MCMC
Stan
R
Logistic regression is a popular statistical model for making predictions on outcomes between zero and one - like probabilities. One application of it in an engineering…
Domenic Di Francesco
Feb 15, 2020
No matching items