Tag Archives: AI

Never Argue with an AI

I owe our system an apology. After it started forecasting a downturn in Covid-19 cases for Scotland, I was dubious, suggesting that because it didn’t ‘know’ about the combination of the final Euro2020 matches or the relaxing of restrictions at a time of rising case numbers, it was being overly optimistic. I was wrong. I owe it the computational equivalent of a beer or two.

From about 17 June, it was forecasting a peak in case numbers for Scotland on or around 5 July, even if it was short on actual case numbers. Since 22 June though, it’s been spot on in both curve and case numbers. The image is of our case number model, plus our current forecast, overlaid with our forecast from 22 June. Basically, it nailed it. The lesson is not to argue with a system that uses more variables than I can count without taking my socks off.

2021-07-14 Case number projections and hindcast for Scotland
2021-07-14 Case number projections and hindcast for Scotland

 

The Impact of G7 and Euro 2020

We’ve now moved from forecast to reality: the UK (and others) are in the throes of a new wave of infections, driven by the Delta variant of the Covid-19 virus. In the UK this has almost certainly been facilitated by both the general relaxation in lockdown and by events such as the G7 Summit and the Euro 2020 competition.

We have now introduced an alert system, which looks for outliers against the current trend in case numbers and pandemic force – this shows that cases and pandemic force spiked in Cornwall following G7 and, as of now, Glasgow (Hampden) just misses out on triggering our alert system and Brent (Wembley) and Edinburgh (the other major source of travelling Scotland fans) both now make our alert list (the red outlined local authorities in the header image). Continue reading The Impact of G7 and Euro 2020

Conscious Uncoupling

As of 11 May, our Covid-19 forecasting system started consistently predicting a coming rise in cases for the UK, driven largely (as it turns out) by the Delta variant of the Covid-19 virus. In the UK this has almost certainly been facilitated by both the general relaxation in lockdown and by events such as the G7 Summit and the Euro 2020 competition. So far, so bad.

Other factors though are far more hopeful – we are seeing a very significant decoupling between case rates, hospital and ICU admissions and in particular death rates. This does demonstrate that the game has changed, and that we need to be rethinking our approach to managing our way out of the pandemic.

That said, government policy in many places still appears to be conditioned by the assumption that the vaccines effectively eliminate transmission, something that simply has not been demonstrated. Continue reading Conscious Uncoupling

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?