January Meetup: Talks

We're delighted to welcome you to our January Meet-up. Pizza and soft drinks will be served on a first-come-first-served basis as usual.

Please note that this is the event page for the talks event. If you'd also like to attend the pre-event workshop, please sign up at the workshop page.

Schedule

1800--1830h: Refreshments

1830--1835h: Welcome

1835--1905h: Real time modelling of winter hospital pressures at UKHSA

1905--1915h: Intermission

1915--1945h: Code review for statisticians, data scientists and modellers

1945--1950h: News & Announcements

Abstracts

Both of our talks this week will be given by Jack Kennedy, a Senior Data Scientist at the UK Health Security Agency. The first will cover his work on infectious disease modelling, and the second will be more of a coffee-and-code style session where he will be talking about good code review practices.

• Talk 1: Real time modelling of winter hospital pressures at UKHSA

Infectious diseases such as influenza, COVID-19, RSV and norovirus provide significant pressure on the NHS in terms of hospital capacity, especially over the winter months. Short term forecasts and "nowcasts" (real-time estimates which take into account reporting lags) of hospital admissions due to such infectious diseases are critical to healthcare leaders in the NHS and local and national government, for short term decision making.

The Infectious Disease Modelling team at UKHSA research methods for short term forecasting and nowcasting the number of patients admitted to NHS hospitals with such infectious diseases. Throughout the winter, we provide weekly analysis of forecasted hospital admissions at local, regional and national geographies which are used to help allocate NHS resources.

This talk will give an overview of our work on forecasting & nowcasting, as well as some of the operational and statistical challenges we face.

• Talk 2: Code review for statisticians, data scientists and modellers

Many modern data professionals come from scientific backgrounds outside of computer science. We’ve often learned to code on the job in a fairly informal way and have little software development training, yet a large amount of our work writing models, data pipelines and automated reporting, for example, are implemented and productionised via code.

A critical part of quality assurance in any data product should be code review. I’ll give a summary of why code review is important beyond just checking that your analysis works and some lived wisdom on better ways to provide constructive criticism.

By the end of the talk, you’ll have an actionable set of code review practices that can improve collaboration, reduce errors, and enhance the overall quality of your team’s products and code base whilst maintaining a positive environment. Whether you're using R, Python, or another language, the principles shared here are universally applicable.

News and Announcements

Have a news item or announcement you'd like to make about upcoming data events or job opportunities in the North East? Comment below or email us at **neds@jumpingrivers.com** and we'll do our best to circulate this information during the session.