Blog - 20 Jul 2022
3 minutes read

Predicting human behaviour with data science.

Blog

Tim Fry, Graduate Data Scientist at Ascent, recently observed a talk by Hannah Fry (no relation!) on predicting human behaviour with data science, exploring via a range of fascinating stories how a mathematical view of what it means to be human can shape the way we design our society, from dating to healthcare.

data science, human behaviour, Hannah Fry, EARL conf

True

True

False

2022-07-19T23:00:00Z

Predicting human behaviour with data science.

Graduate Data Scientist Tim Fry contemplates the notion of two parallel universes intrinsically linked by data science: the physical world which we inhabit and the parallel world of data.

article

Data & AI

//images.ctfassets.net/k26sw1bgepr3/oozIStUpk7mw8W18V9kkY/bce753b4319e872a92af3a3f7caa860b/iStock-157531192.jpeg

Using data science to understand patterns in human behaviour has fascinated researchers for years. But now predictive analytics is forecasting human behaviour better than ever before – helping us generating accurate (and sometimes surprising) answers to often complex questions.

I recently observed a talk by Hannah Fry (no relation!) at the recent Bristol Data and AI showcase on this very subject area. The event was specifically focused on tackling key issues including climate change, equality, and misinformation. A Professor in the Mathematics of Cities at UCL, Hannah believes there are two universes - the material one which we all inhabit, and a parallel world of data. In the data world, which is constructed of numbers and relationships, we can find mathematical insights that can help answer questions about our brick-and-mortar reality, enabled by data science and AI as critical tools link the two worlds.

Hannah highlighted - via a range of fascinating stories - how a mathematical view of what it means to be human can shape the way we design our society, from dating to healthcare. In ‘The Joy of Data’, a sprawling talk that covered everything from shrimp and cows to Wikipedia, serial killers and cancer, Hannah provided numerous examples of using data to solve real-world problems. She highlighted an important consideration: because data is just a proxy for the complex IRL scenario, we need to be sure the questions we are asking are the ones we really want answers to - and sometimes we get caught out by the nuances.

By way of an example, consider the question: ‘when is the best time to inseminate a cow in heat, if we want to birth a bull?’ It turns out that when a cow enters heat, they get up and go for a walk - so, innovative farmers have attached pedometers to their cows to monitor their activity and work out the optimal time for insemination. However, in reality all we can definitively infer from the data is ‘when does this cow go for a walk?’. Answering the wrong question can be a costly mistake, and so, before undertaking a project, it is imperative to take the time to align your goals with what is possible, and reflect upon the questions that can and should be answered to deliver the most value.

The talk was engaging and excellently delivered, and I cannot wait to see Hannah again at EARL this September. Hannah is one of the #EARLconf (Enterprise Applications of the R Language Conference) keynote speakers this year where she will deliver a talk on ‘The Trouble With Automation.’

Hannah Fry is an Associate Professor in the Mathematics of Cities at the Centre for Advanced Spatial Analysis at UCL where she studies patterns in human behaviour. Her research applies to a wide range of social problems and questions, from shopping and transport to urban crime, riots, and terrorism. She is a mathematician, a best-selling author, an award-winning science presenter and the host of numerous popular podcasts and television shows.

#BristolDataAI #rstats #EARLconf

Tim Fry

Graduate Data Scientist

Ascent

As a Graduate Data Scientist at Ascent, Tim leverages his background in Chemistry and Computer Science to explore and interpret data. Experienced in R and Python he has helped healthcare and pharmaceutical companies used their data to create business value.

genericSection

[Think tank] Let’s get started - Get In Touch

Let’s get started.

We help customers build game-changing products, deliver pivotal data and software projects and build strong internal teams. Got a challenge in mind? We’re ready when you are.

Get In Touch

False