Real World Data Science

Welcome to Real World Data Science, a new project from the Royal Statistical Society, in partnership with the American Statistical Association. We bridge the gap between rigorous analysis and real time relevance, meeting the pace and complexity of today’s data driven world with the RSS’s trademark steadying presence.

Latest content

Life Below the Surface: What Freshwater Macroinvertebrates Tell Us About England’s River Health

Working with over 30 years of messy, mixed-format Environment Agency monitoring records, we built a data preparation and modelling workflow that reveals a striking national…

Nov 5, 2026

Data Quality Under the Lens: Can Executives Take the Bonus Bet?

Would you bet your annual bonus on the quality of your organisation’s data? This month’s column explores a real dataset revealing how many corporate executives would.

Ville Satopaa

Oct 27, 2026

David McCandless on the Power and Responsibility of Data Visualisation

The founder of Information is Beautiful on visualisations that influence how we interpret the world.

Annie Flynn

Oct 13, 2026

Is data science a new and exciting set of skills, necessary for analyzing 21st century data? Or is it (as some have claimed) a rebranding of statistics, which has carefully developed time-honored methods for data analysis over the past century? In this article, we use two popular data science algorithms to examine the difference between data science, statistics, and other occupations.

Jonathan Auerbach, David Kepplinger, and Nicholas Rios ask, ‘What is data science?’

Read their analysis

The Pulse

Data Quality Under the Lens: Can Executives Take the Bonus Bet?

Would you bet your annual bonus on the quality of your organisation’s data? This month’s column explores a real dataset revealing how many corporate executives would.

Ville Satopaa

Oct 27, 2026

Data Quality Under the Lens: the DOD’s One-Legged Engineer Problem

This month, Data Management authority Peter Aiken recalls a historical case that shines a light on the data quality issues that can arise when legacy systems are updated or…

Peter Aiken

Sep 15, 2026

Data Quality Under the Lens: Should clinical decisions be influenced by unknown public datasets?

August’s case of the month explores a high stakes question: whether we can trust medical tools built on publicly available datasets.

Alexander Gibson

Aug 28, 2026

Applied Insights

Life Below the Surface: What Freshwater Macroinvertebrates Tell Us About England’s River Health

Working with over 30 years of messy, mixed-format Environment Agency monitoring records, we built a data preparation and modelling workflow that reveals a striking national…

Nov 5, 2026

Linking Brain Injury to Cognitive Decline: A Multimodal, Explainable AI Approach within Trusted Research Environments

Traumatic brain injury generates rich multimodal data—imaging, ICU, EHR and biomarkers—that can be linked to later-life dementia risk. This article shows how…

Kafayat Adeoye, Emma Squires, Fatemeh Torabi, Simon Thompson

Jul 28, 2026

Choosing the Right Genomic Dataset: A Five-Pillar Framework for Researchers

This practical field guide for non-specialists working with genomic datasets argues that the hardest part of genomic research is selecting the right dataset and offers a…

Alieyeh Sarabandi Moghaddam, Fatemeh Torabi, Emma Squires, Professor Kenneth Langlands

May 21, 2026

Generative AI is based on neural networks, which are so-called ‘black boxes’. This makes it difficult or impossible to explain the inner workings of the model which has potential implications if in the future you are challenged to justify decisioning or guidance based on the model.

Excerpt from the UK government’s framework for the use of generative AI

Read our key takeaways

Foundations & Frontiers

David McCandless on the Power and Responsibility of Data Visualisation

The founder of Information is Beautiful on visualisations that influence how we interpret the world.

Annie Flynn

Oct 13, 2026

When the most likely answer is wrong

Scientific validity in the age of large language models

Lee Clewley

Sep 29, 2026

The Hidden Statistics Behind Credit Risk

Three of the most widely used metrics in credit risk turn out to be classical information divergences. Recovering this foundation gives practitioners confidence intervals on…

Denis Burakov, Agus Sudjianto

Aug 18, 2026

People & Paths

Data science and AI in the public sector: An interview with ONS’s Penny Holborn

Penny Holborn, head of faculty for the Office for National Statistics Data Science Campus, talks to Jonathan Gillard about keeping up with new developments, the value of…

Jonathan Gillard

Mar 27, 2024

Data science and AI in financial services: An interview with Nationwide’s Matthew Jones

Matthew Jones, head of decision science and analytical innovation at building society Nationwide, talks career path, data science tools and skills, and the role of AI in…

Jonathan Gillard

Mar 21, 2024

‘I fell in love with math, really, and fell into data science because of that’

A passion for solving mathematical problems led Niclas Thomas to a PhD in machine learning and then a career in data science in the retail sphere. Now head of data science…

Brian Tarran

Oct 4, 2023

Latest content

Life Below the Surface: What Freshwater Macroinvertebrates Tell Us About England’s River Health

Data Quality Under the Lens: Can Executives Take the Bonus Bet?

David McCandless on the Power and Responsibility of Data Visualisation

The Pulse

Data Quality Under the Lens: Can Executives Take the Bonus Bet?

Data Quality Under the Lens: the DOD’s One-Legged Engineer Problem

Data Quality Under the Lens: Should clinical decisions be influenced by unknown public datasets?

Applied Insights

Life Below the Surface: What Freshwater Macroinvertebrates Tell Us About England’s River Health

Linking Brain Injury to Cognitive Decline: A Multimodal, Explainable AI Approach within Trusted Research Environments

Choosing the Right Genomic Dataset: A Five-Pillar Framework for Researchers

Generative AI is based on neural networks, which are so-called ‘black boxes’. This makes it difficult or impossible to explain the inner workings of the model which has potential implications if in the future you are challenged to justify decisioning or guidance based on the model.

Foundations & Frontiers

David McCandless on the Power and Responsibility of Data Visualisation

When the most likely answer is wrong

The Hidden Statistics Behind Credit Risk

People & Paths

Data science and AI in the public sector: An interview with ONS’s Penny Holborn

Data science and AI in financial services: An interview with Nationwide’s Matthew Jones

‘I fell in love with math, really, and fell into data science because of that’

Published by

Our partners

With support from

About us

Contribute

November Newsletter

Latest content

Life Below the Surface: What Freshwater Macroinvertebrates Tell Us About England’s River Health

Data Quality Under the Lens: Can Executives Take the Bonus Bet?

David McCandless on the Power and Responsibility of Data Visualisation

The Pulse

Data Quality Under the Lens: Can Executives Take the Bonus Bet?

Data Quality Under the Lens: the DOD’s One-Legged Engineer Problem

Data Quality Under the Lens: Should clinical decisions be influenced by unknown public datasets?

Applied Insights

Life Below the Surface: What Freshwater Macroinvertebrates Tell Us About England’s River Health

Linking Brain Injury to Cognitive Decline: A Multimodal, Explainable AI Approach within Trusted Research Environments

Choosing the Right Genomic Dataset: A Five-Pillar Framework for Researchers

Generative AI is based on neural networks, which are so-called ‘black boxes’. This makes it difficult or impossible to explain the inner workings of the model which has potential implications if in the future you are challenged to justify decisioning or guidance based on the model.

Foundations & Frontiers

David McCandless on the Power and Responsibility of Data Visualisation

When the most likely answer is wrong

The Hidden Statistics Behind Credit Risk

People & Paths

Data science and AI in the public sector: An interview with ONS’s Penny Holborn

Data science and AI in financial services: An interview with Nationwide’s Matthew Jones

‘I fell in love with math, really, and fell into data science because of that’

Published by

Our partners

With support from

About us

Contribute