Tag Archives: AI

Waiting for the Fat Lady

The UK government has just announced that it isn’t going to make a decision on further relaxing Covid-19 restrictions for another two weeks, just as many people were, quite reasonably hoping that the fat lady was, if not in full song, at least warming up for her aria.

Flippancy aside, let’s be clear: delaying a decision like that is utter nonsense, at multiple levels: whether it’s driven by the use of lagging data, the continuing failure to adopt and use effective forecasting (ours or anyone else's), the pursuit of political dogma, or any combination of these, they're once again delaying decision making until it's too late.

Worse, they seem to be relying on the success of the vaccination program to try to pull a largely fictional rabbit out of their hat - the hat that comes with a large label saying, "Wishful Thinking". But now for the data and analysis… Continue reading Waiting for the Fat Lady

Early Warning Onwards

The UK government stated yesterday (13 May) that rising case numbers in the Bolton area were a cause for concern, and that very many of these cases were of the so-called ‘Indian’ variant (B.1.617.2 being the designated variant of concern, with B.1.617.1 and B.1.617.3 under investigation). Here, raw data for case numbers has been available for weeks, with  organisations such as the Sanger Institute also providing a very informative breakdown by sequenced  variants.

Our analytics platform had identified Bolton and other areas as potential concerns more than two weeks ago and had flagged a correlation between these hot spots and the ethnic balance of the local population, such that, even in the absence of cross-border travel data, of the emerging variants or the situation in India, we were able to provide early warning of emerging problems.

Which very much begs the question as to why the UK government only raised this yesterday, and why travel restrictions from India were only imposed long after the pandemic reached critical mass there. Continue reading Early Warning Onwards

Late to the Party. Again.

SAGE announced today that England's R number has risen across to between 0.8 and 1. They update their pronouncements once a week, based on their modelling from data that's even further behind.

We take a different approach: we use emergent and inferential analysis to generate R number calculations and 28-day forecasts, on a daily basis, for every local authority in the UK.

We can say that England, as of today, is at an R number of around 0.92, up from a low of 0.80 on 19 April. Our forecasting suggests that it's going to go over 1.0 from tomorrow, reaching roughly 1.3 by the end of the month, with England leading the way, followed by Wales and Northern Ireland, with Scotland doing rather better, for the moment at least.

2021-04-23 R Number and forecast for England

Continue reading Late to the Party. Again.

Raining on the Parade?

The time to relax lockdown is once you have a combination of low case numbers (check), an R (infectivity) number that’s well below 1 and trending downwards, and have effectively stamped on any potential hot spots around the country, to the point where the increased travel between areas that we're already seeing doesn't risk a spread from those hot spot areas acting as reservoirs of reinfection.

And this does not look like that time. Yes, case numbers are low (rolling weekly rate/100k population across the UK is around 26), but… Continue reading Raining on the Parade?

Intelligent Reality at EIE2021

We are pleased to announced that our new company, Intelligent Reality, has been accepted into EIE’s 2021 cohort, which showcases the most innovative, data-driven tech companies from Scotland, the UK and beyond. EIE's (Engage, Invest, Exploit) annual conference features the the most promising high-growth companies who are seeking funding, from seed to series A.

Over the last 18 months we have successfully developed both our generic platform and environmental and geospatial applications, with an SBRI-funded R&D programme for Scottish Natural Heritage (now NatureScot) and, latterly, with three rounds of funding from InnovateUK. These have led to the successful development of inferential tools for exploratory, analytic and predictive modelling of the Covid-19 pandemic, as well as enhancing our core platform.

We have not only developed our analytic and predictive pipeline, but have further developed our relationship with udu, the revolutionary, discovery-based data intelligence platform, itself co-founded by Two Worlds.

With academic and industrial partners, we have also explored real time applications in precision agriculture and pollution monitoring.


Intelligent Reality,  with staff in Scotland and Germany, has been formed to exploit the successful outcomes of Two Worlds' incubation of its adaptive, self-organising approach to data analytics, providing insight and predictive intelligence for real world applications in dynamic environments.

EIE, which is run by the Bayes Centre at Edinburgh University in partnership with the DDI (Data-Driven Innovation) initiative, is a year-round programme highlighted by a day of pitching to investors from across the globe. EIE21 takes place on 10 June.

Proving a Point?

There’s been a lot of covoptimism this past week, from assorted government spokesfolks, including from people who do know what they’re talking about – a prime example being Prof. Neil Ferguson of Imperial. The theme here is that cases, case rates and the R number have been falling strongly and appear to be continuing to do so.

That’s true, to a point. But our modelling suggests that the immediate future is less rosy.

It's not about the data – we use the same published sources as the government, albeit that they've got access to more sources than we do – it's more about what you do with it. 

Continue reading Proving a Point?

Time for a different approach?

We – as a society – had the opportunity to prevent SARS-CoV-2 becoming endemic. We largely wasted it, initially by not locking down early enough or for long enough to remove it from the population. Nor did we use the lockdown period to set up effective data collection, testing, tracking and analytic tools to enable rapid and fine-grained response to predicted changes in incidence (it's a truism that, by the time you're working with actual data, you're already behind in your response). 

Public policy decisions are therefore based on incomplete and lagging data, partial models and on individual and committee opinion (however well qualified the participants) rather than being informed by data-driven modelling of potential outcomes. We are also behaving as though we're dealing with a static target rather than a continuously evolving situation, one where an unintended consequence of partial and incomplete restrictions is that it effectively selects for different strains of the virus, as it evolves to cope with changes in population behaviour. This virus, like any other, has been mutating since before it collided head-on with our species, and it continues to evolve as it seeks selective advantage in exploiting its human host population, at any given time. Continue reading Time for a different approach?

Damned (Official) Statistics…

In developing our daily-predictive AI for Covid-19 infections , we’ve come across some, ah, interesting quirks in the official UK data: previously, we’d been using the government’s daily download data set for England, hoovering it into udu and thence driving the internal and R-based analytic and learning models. We've done the same for Scotland, Wales and Northern Ireland, from their respective data gateways, and merged the outcome to create a consistent baseline for analysis. Overall then, a bit clumsy, but perfectly workable. Continue reading Damned (Official) Statistics…

Two Worlds completes R&D Project with SNH

Two Worlds has successfully completed the first phase of an R&D project with Scottish Natural Heritage (SNH) , funded by the UK’s Small Business Research Initiative (SBRI) programme.

The project’s goal was to demonstrate the feasibility of a service to provide a single point of advice to support anyone planning activities that affect the natural environment, to help them understand the environmental impact of their proposal, to advise them on what they could do to mitigate any impact and to outline what consents and processes they’d then need to follow. It will also be possible, over time, to build a dynamic picture of the impact of human activity on the natural environment by a wide range of measures, including climate impacts. Continue reading Two Worlds completes R&D Project with SNH

Wye AI, Man!

Most AI practitioners will argue that the risk to humanity from AI doesn’t (and won’t) come from an AI waking up one day, deciding that the best way to solve the world’s problems is to wipe out humanity and then serendipitously finding that it’s in control of the world’s nuclear weapons. On the principle that cock-up trumps conspiracy, pretty much every time, we’re far more likely to take a range of hits from the misapplication of an AI that’s either too stupid1 to do the job that’s been asked of it or where those deploying it are incapable of understanding its limitations (or indeed don’t care, as long as they’ve cashed out before it all falls apart). Broadly speaking, machine systems fail for one or more of these reasons: Continue reading Wye AI, Man!