NMPi Predicts: Lib Dems Soak Up Labour Seats

A couple of years ago we wrote an article that finished a little something like this;

*DISCLAIMER – whilst we’re hopeful of being correct, thus acquiring fortune and numerous appearances on breakfast television, this is mainly in jest. Please read with a pinch of salt.*

The disclaimer was for a piece where we tried to predict the results of the 2017 UK General Election using Google search data. In the face of multiple polls suggesting otherwise, along with a handful of Twitter trolling, we predicted a Hung Parliament. 

Oddly enough, we ended up being right. 

Rather unfortunately, it turns out the amateur polling world isn’t as lucrative as we first thought. Buckets of cash and a visit to Holly and Phil’s sofa weren’t on the cards.

What did emerge, however, was a murmur of intrigue around the methodology our approach used. If it did indeed have legs, it would add an interesting and very different voice to the media circus. 

So, after our spectacular entrance to the political polling world, here we are with our, likely ill-advised, sequel. Let’s hope we’re a little more Godfather than Jaws. 

Finding the Swing Seats

Last time out, we tried to predict the result of every seat in the country by looking at search trends in key regions alone and extrapolating outwards. For this year’s effort, we took a more rigorous approach; going a floor deeper and focusing our attention at a constituency-level. 

Despite how much free time we may appear to have, completing such a depth of analysis across 650 micro-regions was beyond our comprehension. Try doing that during Black Friday. That’s why this time we decided to focus on potential swing seats only. Whilst we were correct with 2017’s end result, the addition of specific seat allocations to the mix will hopefully bring even greater accuracy, with all of our time and effort being spent in the granular details of key battlegrounds. 

Our first challenge was to define where these elusive swing seats lay. Rather than taking the easy route and asking someone, we chose the data-driven option (as we tend to do). 

Step one was straightforward enough. We took the results from the 2010, 2015 and 2017 elections and built a picture of the voting history for each constituency. Any seat that had swung during those last three events were included within our analysis. 

The next stage was to then look all those that were left. How do we calculate the potential instability of all remaining seats, some of which haven’t changed hands in over a decade? 

For this, we modelled the average seat swing for each party in every constituency over the last three elections. The fluctuations over time gave us an idea of seat volatility which we then applied the following formula to:

All those with a value below 1 were added to our list of potential swing candidates, leaving us with a total pool of 209 seats to go forth and predict using our latest algorithm update. 

The Formula

We learnt from our past efforts that the prediction formula should take into account three separate elements. The candidate in the borough, the parties themselves, and respective party leaders. 

We started by sourcing the previous months number of searches for every local candidate in those 209 seats from Google’s Keyword Tool. The number of impressions were considered their vote share. This was then weighted against searches for each party and party leader, leading to the following formula: 

What we ended up with was a value considered to be their share of the electorate’s vote in any given seat. Whichever local candidate had the highest share was thus predicted to be our victor. These numbers were then added to the seats unlikely to swing. 

Makes sense in principle, but how did it stand up in practice? Sadly limitations in search term data restricted our testing to the 2017 election only. The output however was extremely encouraging. 

Upon running the formula, we ended up with this:

A 4% margin of error, or a 96% confidence level. A positive sign for any pollster. 

We settled on our approach and applied it to the battle to come. 

The Prediction

In an election where almost everyone appears to be queueing up to lose, we have our winner. A very slender Conservative majority. Regrettably, not quite the bombshell that we landed with last time around. 

There are however three things that are very interesting. The first is the predicted performance of the Liberal Democrats. In a campaign where the whole notion of ‘tactical voting’ appears to have taken root, it doesn’t seem to have worked in the way that we had anticipated. Rather than reducing the Conservative majority, the Lib Dems are predicted a surge of seats from 21 to 35 at the expense of Labour; implying that anti-Brexit voters are sticking firm. This hasn’t been predicted to this scale anywhere else.

The second is the drop in seats for the SNP – a sign perhaps that the ‘indyref2’ campaign message hasn’t resonated with voters in the region? Whatever the cause, Nicola Sturgeon will likely see this as an opportunity missed if results do indeed end up this way. 

The final point to mention is some of the shock swings our analysis has revealed.

We have Sheffield Hallam switching to the Conservatives (following a slim Labour victory in 2017), Southport opting for the Lib Dems (after the 2017 Conservative victory), and perhaps most surprisingly Wimbledon moving into the hands of the Labour Party (a Conservative hold for over a decade). If the latter in particular were to happen early on in election results night, it could see pollsters scrambling to add a couple more notches of red to their bar charts.  

And there we have it. Phase two complete. Whether we’re hoisted aloft and buried in awards (like The Godfather II), or quickly forgotten and relegated to the annals of history (like Jaws II), only time will tell. All we do hope for is that we last a little longer on your screens than a picture of an ill child being waved in front of a Prime Minister. 

NMPi Shortlisted at UK Digital Growth Awards

We’re thrilled to announce that we have been shortlisted for yet another award for our innovative data-driven strategies!

Last month, we celebrated our success at the UK Biddable Awards, The Drum Marketing Awards, and the PMA’s. Then celebrations continued this May, when we were shortlisted for four awards at the Effective Digital Marketing Awards.

Now, we’re on another shortlist – this time with the UK Digital Growth Awards! These awards reward excellence in UX, CRO and Search, where campaigns have driven tangible growth and results.

We’ve been shortlisted for ‘Best Use of Data’ for our campaign with Liverpool FC – making this the 7th Award our Liverpool campaign has been shortlisted for.

Our partnership with Liverpool on their display campaign has already achieved 3 award wins in 2019, proving to be a real showcase of talent for our groundbreaking and successful campaigns.

We’ll let our very own Anna Jorysz’s presentation on our “data-driven approach” to success show you how well deserved this nomination is.

Keep your fingers crossed and watch this space on the 17th July!


Facebook Announces New WhatsApp Ads for 2019

In February 2014, messaging platform WhatsApp joined the Facebook family with their adless reputation still intact. Since its launch in 2009, WhatsApp has drawn in users with its “no-ads” mantra and its end-to-end encryption, but those days seem to be numbered with the announcement of ads which will appear on the Status page coming to the service in 2019.

What Do We Know?

The WhatsApp Status feature was introduced in early 2017 and works much in the same way as many other Story platforms like Facebook and Instagram Stories, and Snapchat. Users can upload photos to show their contacts what they’re up to, with the promise that these videos will be gone in 24 hours. However, uptake has been weak with less than 50% of account holders making use of the feature.

Despite this, and against the platform’s long-standing commitment to providing an ad-free service, Facebook has confirmed that ads will be rolled out into the Status feature at some point in 2019 to the dismay of users and stakeholders alike. WhatsApp’s co-founders didn’t originally know that Facebook wanted to start sharing data across platforms to help target ads at users, which in part led to Brian Acton leaving the company last September.

Users are also unhappy about the news, as it appears many of the platform’s main selling points have now gone to the wayside. WhatsApp’s founders never wanted to know more than your phone number and promised end-to-end message encryption, but many are worried about how much information will be scraped from their private conversations.

What Don’t We Know?

A big question that many advertisers will have is how linked it will be to Facebook, as this will have an impact on the level of targeting available, how much information about a user is made available, and how tied to the Facebook Ads Manager it will be.

For instance, by linking a WhatsApp profile to a Facebook account, this gives an advertiser access to all of Facebook’s targeting methods, raising the question, how easy it will be to integrate WhatsApp advertising into your social advertising campaigns. Will WhatsApp be part of the Facebook Ads Manager – like Instagram is – or will it be managed independently?

WhatsApp operates on a very low barrier to entry, only requiring a phone number to sign up. As such, will the platform be able to link this mobile number to a Facebook account? This will provide more information than is currently available on WhatsApp alone. With account information, advertisers will be able to apply similar targeting strategies to those on Facebook such as interest segments and lookalikes.

It will be interesting to see what kind of creative formats are available: will there be a variety, as there is for Instagram Stories, or will it be more like Facebook Messenger where you can only use single image ads.

There will be a lot of questions about how much information will be scraped from messages and just how much personal data will be shared between Facebook’s platforms. This will be crucial to getting consumer buy-in, as many users will be frustrated if they feel like information from their private conversations is being exploited.

Furthermore, the only ad format being put forward at the moment will appear in the WhatsApp Status, similar to Facebook or Instagram Stories, which are viewed by less than 50% of users. Whether this is extended out into Chat remains to be seen, as this may result in people deserting the service and thus making it unprofitable as an advertising platform.

Currently, we have more questions than answers, but monetising WhatsApp was going to happen at some point, even if it has been soon than many would have liked or even anticipated. This is certainly a platform to keep an eye on as the potential is enormous, but testing will be necessary to assess the actual value.

NMPi Wins Best Travel/Leisure/Sports Campaign at Drum Search

Following a highly successful evening at the Performance Marketing Awards, we are pleased to announce that NMPi picked up an award for Best Travel/Leisure/ Sports Campaign in last night’s Drum Search Awards!

Once again, it was our work with our amazing clients, East Midlands Trains, that saw us take home the gold. We were also highly commended for Most Innovative, based on our work with Harvey Nichols, and Industry Rising Star, for the very deserving Fred Maude.

It’s a huge honour for us to receive these awards, and we are incredibly proud of our teams. Their hard work and innovation are what drives NMPi forward, and these awards will be a springboard for bigger things in the months to come.

You can check out Fred’s response to winning Best Travel/Leisure/Sports campaign below.

NMPi Wins Best Search Award at RAR+ Digital Awards

NMPi is delighted to have won in the “Best Search” category at last night’s RAR+ Digital Awards.  The RAR+ award is especially important because it recognises agencies who deliver outstanding results as voted for by clients on a measure of overall satisfaction, rather than being judged for a single campaign case study.

NMPi’s CEO, Luke Judge, commented, “I am immensely proud of our brilliant team at NMPi; their hard work and passion for doing outstanding work with our clients has been deservedly recognised by this important award win. I am also grateful to our clients for their kind survey feedback in supporting us”.

Director of Biddable, Sophie Harkness added, “We have always prided ourselves on going the extra mile for our clients, so it’s great to see this acknowledged with this Best Search win”.

Head of Performance Marketing, Max Flajsner commented, “I believe our client happiness, and therefore this recognition, is a direct consequence of the high levels of innovation that we have brought to our client’s campaigns over the past twelve months”.

This award win follows closely after NMPi was ranked in top place in the Drum’s UK Elite Media Agency rankings. This kicked off an expansive year for the company, which has so far seen the launch of three new NMPi offices in Zurich, Sydney and Cape Town.

The second half of 2017 looks set to be even more exciting, with this award acting as a springboard to further success.

Where Are We Now? A Year on From the Brexit Vote; What are the Opportunities for Digital marketing in the UK?

A year ago, marketers across the land were faced with the question of how Brexit was going to impact them; their activities, their budgets, their customer-base… pretty much their entire world. And so, I wrote a piece about what Brexit would mean for digital marketing activity.

Its almost 52 weeks later, and to be honest, we’re still asking the same questions. Though Article 50 was “invoked” on the 29th of March, there have been next to no details about what Brexit will means for the UK or, by association, for the rest of the EU. And with yet another election looming over us, things are as unclear as ever.

What does this mean for digital marketers – including those at agencies and their clients? What could happen? What definitely will happen?

FX Risks and Rewards

Immediately after the Brexit referendum, exchange rates shifted and the pound took a tumble. Instantly this was an opportunity for brands to sell more of their product aboard where their prices suddenly became much more attractive.

For many brands, this is still a massive opportunity with untapped markets out there – and there is no reason they shouldn’t be moving to seize that opportunity for all it’s worth.

However, there is a flip-side; many brands who buy their products from other markets are suddenly finding their imports are costing significantly more. For these brands, simply driving international revenue may not be enough to plug the profit gap.

Data Privacy – An Opportunity for Change?

Current data protection laws come from the European Data Protection Act. This governs how data can be transferred, used, and ultimately collected. In a post-Brexit world, a government serious about helping businesses could make the sharing and use of data easier.

This might not be popular with the public, but if changes were phased in gradually and ultimately this lead to ‘Joe Public’ having a more personalised online experience, it could become the new normal without too much fuss.

The Rise of the Silicon Kingdom?

If a government were to make the UK a more “desirable” base for international companies, then we could see the UK become the global hub of international digital marketing.

Not only would traditional client-side businesses be persuaded to move here but there would also be major benefits for tech companies to locate in the UK. The Silicon Kingdom could eclipse Silicon Valley.

And this could only be a positive for driving creative thinking in digital marketing.

Cutting Ourselves Off from International Talent

To continue to grow, the UK’s digital marketing sector needs the best and brightest minds, and in recent years, we’ve had the pick of not only the EU but of the world.

Though if work visas and international recruitment become issues, the UK may struggle to acquire the talent it needs. However, that’s not necessarily a dead end. In today’s digital/gig economy, your team does not have to sit in your office. Remote working and even project-based employment/contracting could be the answer.

The Known Unknowns

Until we know, one way or another, whether Brexit will turn the UK into an economic wonder or wasteland, there will be caution at all levels.

Consumers and brands will hold off on big projects requiring heavy investment – whether that be installing a new home bathroom, or launching new products and services.

And everyone will be guarding against a potential cataclysm by saving and cutting back as much as possible – both at home and the office. As agencies, we need to make sure we continue to make sensible marketing decisions on behalf of clients and focus on driving efficiency as we always have done.

The Importance of the Basics

With efficiency being increasingly important, it’s vital for digital marketers to hold true to the core principles of efficiency, flexibility, and transparency.

Producing best-in-class work remains the objective of any good agency and that doesn’t just mean sexy new projects, it also means remembering to cover the basics from the bottom up to make sure that every pound and penny is pulling its weight.


I leave you now with the closing statement from the article I wrote last year on this subject as, even though we’re 12 months closer to Brexit, we’re still a long way off:

“Ultimately, we won’t know a lot about what the future holds for a post-Brexit Britain until it’s upon us. But if the digital marketing industry holds true to its core concepts of flexibility, efficiency and transparency then we should be able to ride out any storm and continue to drive success for our clients.”