Last Top-Tips for Black Friday

Read Time: 3 Minutes 50 Seconds

With Black Friday and Cyber Weekend looming right around the corner, we asked the team for some last minute top tips to help see you through the four day extravaganza. Covering everything from audience optimisation and tailored ad content, to interactive creatives and lead generation ads, here are their thoughts.

Stand Out Creative Design

“Over the Black Friday period users are saturated by content, so ensuring your creatives stand out is vital. Including interactive formats and creatives that drive user urgency such as, countdown timers in your creative strategy is a great way to ensure you don’t become lost in a sea of content.” – Beth Vaughan, Creative Development Executive


Amazon Ads Strategy


“When it comes to Amazon, make sure you’re utilising all of Amazon’s advertising features and start showcasing your brand well before Black Friday (keeping the momentum going all the way  through – until the end of the year). Black Friday sees a 129% increase in traffic, and a 250% increase in sales compared to the October average so I recommend using a three step approach over the course of the weekend, focusing your product strategy on:

  • High potential products before Black Friday
  • Product deals during Black Friday
  • Top performing products after Black Friday

With 30% of users on Amazon planning to make Christmas gift purchases in November, advertisers need to understand their customers and tailor their seasonal keywords accordingly, as well as increasing bids & budgets to allow for the spike in demand.” – Peter Munton, Senior Performance Manager



“Make sure you remain flexible over Black Friday and Cyber Weekend as it’s hard to predict how consumers and competitors will behave during this time. Running ads focused on lead generation in the lead up to Black Friday will allow you to generate excitement and guarantee you an audience ready to retarget over the weekend, and on Cyber Monday. 

You should also consider your target audience, tailoring your content to target deal-savvy users, who purchased last Black Friday, and advertising on deal websites where users will likely be browsing options before purchase. 

Lastly, as time spent on YouTube has rocketed during lockdown, ensure you also take the time to consider your YouTube strategy, as well as a brand measurement piece, to get a better idea of the impact this activity has on users.” – Alice Malthouse. Account Director


PPC Optimisation

“My top tip would be to build out specific Black Friday campaigns with extended keyword coverage on both exact and broad modifier match types, rather than integrating these within your existing search campaigns. Not only will this enable efficient budget management, but you’ll also find it easier to monitor your bids – as these will likely have higher CPCs due to the rising competition associated with the holiday season. 

Advertisers should also remember to preserve enough budget to spend on both the day of, and Cyber Weekend,  remembering to double check campaign budget caps to avoid capping out. A good idea would be to check how much each Black Friday campaign spent last year and get an additional 20% on top of that for this year, giving a rough idea of what to spend each day. 

Additionally,  make sure you’re fully taking full advantage of the variety of audiences you can create; from last year’s Black Friday purchasers, to users who have visited your deals page but have not completed a purchase. Targeting cart abandoners is always a good audience to focus on, as they tend to have a higher intent to convert than ‘just browsing’ customers.” – Emma Pilaviou, Account Executive


Social Urgency

“In a society where everything is at the touch of one’s fingertips, now is the perfect time for advertisers to get their brand in front of their audience, creating a sense of urgency and demand for their product. My top tip for Black Friday would be for brands to use the time sensitive nature of Black Friday deals to play the ‘for a limited time only’ card, boosting the consumers’ sense of urgency, and incentive to buy. 

Brands should be optimising the Facebook platform, to generate this sense of urgency – creating clear and straightforward ad content that targets intended audiences. Although Facebook has declined over the years on the hierarchy of Social Media Platforms, it still remains the best platform for targeting specific user demographics. Brands should also be using Instagram and the stories feature to interact with users, identifying which ads are resonating with their audience and which are not.” – Louis Basileo, Partnership Sales Associate

There’s not long left until the big day, but with these top tips you’ll be able to pick up some quick wins across the Black Friday weekend. If you want to get some external insights into how your campaigns are performing, get in touch with the team today.

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. 

From Dates to Data: NMPi’s Love Island Prediction 2019

Summer is finally here and there’s only one thing that means: Love Island is back on the telly! That’s right: 3 weeks ago, 12  intelligent – but most importantly – really good looking young individuals, dropped their Instagram-heavy lives for 8 weeks of non-stop tan and drama in the  Love Island villa.

It’s hard to believe we’re already 3 weeks into this year’s love story, but bets are already on as to who will be the lucky couple to take home the prize this year. We decided to use what we know best – data – to see if we can predict which couple will survive the summer of love and be crowned the winner of Love Island 2019.

We can’t however, predict who will still be together 6 months down the line…

State of Affairs and Methodology

Before we dive into our data analysis, let’s take a quick snapshot of the current state of affairs in the villa (at the time of writing). For those of you not up to date, come back in 15 hours when you’ve caught up!

We have 14 contestants currently in the villa: 4 couples and 6 single contestants. These couples, as of the 21st of June are:

  • Amy & Curtis
  • Amber & Michael
  • Molly-Mae & Tommy
  • Yewande & Danny

Our source for these predictions is Twitter. We’ve pulled apart each couple’s Twitter profiles to compare how many tweets they have, their average reach, and their value in the eyes of the general public. The bigger the gap within the couple, or the smaller the number, the lower the compatibility score.

With this in mind, we popped on our investigative sunglasses and started crunching the numbers. Starting with couple number one:

Amy & Curtis

Ever since Curtis entered the villa in week 1, he and Amy have hit it off like a house on fire. Both passionate about musicals, theatre and ballroom dancing, they are a flamboyant couple often called the “Mum and Dad” of the villa by other contestants. But what do the numbers say?

Curtis comes in with a Twitter reach of just under 11 million, which doesn’t hold a candle to the 27 million that Amy reaches. Given the huge gap between them, it’s almost surprising that their Tweets/contributor ratio and value are so similar. Amy comes in with a Tweets/contributor ratio of 2.17 and a value of £171k. while Curtis has a ratio of 2.1 and a value of £177k.

Taking this into account using our in-house algorithms this couple takes home a whopping compatibility score.


Amber & Michael

These two had a slow start in the villa, starting off as friends. As the days went on Michael turned up the heat until Amber finally admitted that she had caught feelings too. 

Turning to the numbers, Amber pulls in a reach of 10.5 million on Twitter, while Michael only manages 5.5 million. Already a poorer start than our first couple. The difference in Tweets/contributor ratio and value is also more apparent, with Amber at 2.45 and $108k, and Michael 1.66 and $52k respectively. Adding it all together, it looks like bad news for Amber and Michael.


Molly-Mae & Tommy

It’s not been a smooth ride for these lovebirds, with Tommy being torn between Lucie & Molly-Mae in week 1. It was only because Lucie chose Joe that Molly-Mae & Tommy ended up together. Then, when mega toe-stepper Maura entered the villa, Tommy was once again caught between two girls. However, he chose to re-couple with Molly-Mae, to the utmost joy from the UK public.

But how are these two looking now they are (supposedly) dedicated to each other? Molly-Mae brings home a reach of 8 million, Tommy only 7 million. This is a much smaller reach than the other two couples, which is surprising given all the drama focused around them so far. Looking at our other metrics, Molly-Mae has a Tweets/contributors score of 2.31 and a value of $139k. Tommy on the other hand only hits 1.37 and $35.5k for value.

It’s worth noting here that Tommy is the most followed contestant on Instagram so far – over 1 million! – but in terms of compatibility, they’re very middle of the road. 


Yewande & Danny

Last but not least, scientist Yewande & model Danny. Yewande was having a hard time of finding love in the villa, so when Danny entered, the Islanders – and indeed the whole of the UK – rejoiced. This thrill was short lived with fractures already showing in the couple. New girl Arabella has swept Danny off on a date, leaving Yewande fighting with her feelings, and for her man.

Yewande achieves a Twitter reach of 1.5 million, and Danny 2.7 million – the lowest of any of our couples. Looking at the additional metrics, Yewande gets a Twitter/contributor score of 1.39 and a value of $5.6k while Danny is looking at a ratio of 1.15 and a value of $15k. The outlook is certainly bleak.

The result from our compatibility algorithm backs up what we’re dreading: a pretty damning score. Looks like these two would have better luck finding love somewhere else…


Our Prediction

So that’s it, Amy & Curtis have topped our couple prediction and they are the data and dating front runners of Love Island 2019!

But, as we’ve said, a lot can change in 5 weeks – so we’ll be following up in a few weeks with some updated predictions.

Will Amy & Curtis stay strong? Will Molly-Mae & Tommy do bits? Will Yewande & Danny ever break up? Only time will tell. We’ll see you back here in a few weeks!

Why Ad-Blocking is at a Three Year Low.

If you were to say you’ve never been irritated by an ad or pop-up, you’d be lying. With pop-ups and banners appearing on most sites, it’s no surprise that consumers have turned to ad-blockers in an effort to avoid them. Google’s even developing an update that will potentially prevent the use of ad-blockers on their search platform.

Last year, a survey from the Association for Online Publishing (AOP) took an in-depth look at the trends in ad-blocker use. The results showed that online ad-blocking was at an all-time high in 2016, with 30.6% of ads being restricted by ad-blocking programs.

Ad-blocking is a clear message from consumers that our ads do not serve them. Having been so overrun with banners and pop-ups, they have developed the belief that ads are ‘frustrating, unwanted and irrelevant’. So, advertisers have been forced to change tact.

It seems to have worked; with the AOP also highlighting that ad-blocking hit its lowest point in the last three years during Q4 of 2018 – falling to an incredible 10.3% . So what have we done to change the industry, to change the mindset of an online mass?


There are a number of ways for advertisers to place customer interest at the core of our campaigns; as discussed by Product Development Manager Fred Maude in last summer’s NMPignite seminar. By providing users with valuable experiences, we can begin to alleviate the rise in ad blocking. With the development of AI and more sophisticated data collection methods, we can make ads which are more personalised than ever.  Precise user information allows us to alter advertising creatives and placement to have maximum impact.

The Customer is ALWAYS right” Fred Maude

In short; If we deliver something that is tailored to their wants and needs, they will be more likely to engage with the ad.

User Experience

In order to make campaigns more customer-centric, we must consider the user experience as a whole. Using cookies and integrated data, we are able to build a greater picture of the user in order to connect with them and encourage engagement. Content should be created around their needs and help them identify how the brand can solve their unique problems.

A big part of the online experience involves the way consumers react to ads. Interestingly, choice can play a big role in this, with 79% of customers claiming they would consider uninstalling an ad blocker if they had the choice to close, skip, or ignore ads. This provides the option to engage in the content or not and can offer more accurate data on impressions and conversion rates.

Similarly, consider an advert that is not only customer-centric, but also contextual to the consumer’s current phase of the online journey. By placing ads on contextually relevant sites, and remarketing products that customers have already engaged with, we can change the function of the ad to a ‘helpful shopping tool’. This, paired with the rise of online shopping and ‘browsing culture’ has allowed ads to hold their own.

It’s clear that the consumer experience of Display and PPC ads has changed dramatically in recent years. The decrease in blocker use clearly reveals that advertising strategies have shifted  In a way that users are responding well to.

With this in mind, ensure that your ads focus on customer centricity and the user experience. This will allow us to continue to improve our audience’s relationship with advertising.

NMPi Predicts: 2019

With the dust firmly settled after the New Year, we asked the team for their 2019 industry predictions. Covering everything from democratised data and a US equivalent of GDPR, to an increase in investment in Analytics and expectations for the big three (Google, Facebook, and Amazon), here are their thoughts.

“Looking at the year ahead, the industry should expect 3 major step-changes. 

The Search landscape will face huge disruption in the coming year, owing to the rapid encroachment of voice assistants changing the way that users engage with search.

Analytics will become an even greater priority for businesses, and budgets will reflect this. Total spend on Marketing Analytics will likely increase by 35% YoY.

Thinking visually, digital video advertising will be incorporated on a wider scale, based upon a  25% uplift in video consumption across Social and Video platforms. Display will also get some much needed TLC as brands will start to care more about their creatives again. Specifically, keep an eye on product carousel ads: the industry should expect big changes (for the better) in product carousel ads.”   – Luke Judge, CEO


“Agencies will desperately try to categorise themselves as anything but an “Agency”, but most will do little to change the bad practices that led to the negative associations that businesses have with the word.

Looking towards the key players, we’ll see major improvements to Amazon’s advertising platform, while Google makes a significant move away from last-click measurement and announce a series of new initiatives to help SME retailers compete against larger brands.” – Damien Bennett, Director of Business Strategy.


“Instagram is a prime channel for retail and ecommerce, something we have known for a long time. The visual focus has drawn in influencers and in recent months the platform’s advertising capabilities have bloomed. This, in turn, has created a perfect storm which will see retail and beauty brands shifting their Paid Social budgets away from Facebook, so as to invest more heavily in Instagram.” – Ruthie Pinion, Junior Marketing Manager.


“There are 2 big themes that I think will come to the forefront by the end of 2019. First, major tech firms will be going big on cross-leveraging in an effort to sustain their historically stellar growth. Amazon will try to use its’ Shopping and Cloud dominance to push across into advertising, while Google tries to use their advertising dominance to leverage into the Cloud.

Secondly, we’ll start to see more democratised data that doesn’t require a PhD in data science to understand. As data tools get easier to use, it will also become easier to manage complex campaigns at scale; making it easier to in-house. Expect to see agencies responding to this with more sophisticated cross-platform services. The flip-side is that this will require ever-larger volumes  of data, which will result in more frequent – and larger – data scandals in 2019!” – Paul Rauff, Head of Technology.


“As prices rise on necessity goods like food, utilities, and transport, consumers will continue to cut costs where they can, especially with regards to entertainment, fashion, and holidays. This has caused many mid-range retailers to struggle over the past year, and we have seen many dropping prices or closing branches to compete.

This continuing trend will mean Direct-to-Consumer brands who can offer cheaper prices on many of the same products will really flourish in 2019. As noted by eMarketer, D2C brands don’t have the baggage of established brands, which means they can use their speed, flexibility and responsiveness to change to their advantage in a way which is highly cost-effective.” – Lisa Morton, Head of Marketing.


“Over the course of 2018, we saw a significant decline in organic clicks. This was down to a number of things. Google’s huge push on their ads last year was bad news for organic results; eating into organic real estate and forcing advertisers to increase their budgets. On top of this, there are a lot more features in the SERP – such as featured snippets and knowledge boxes – which have further reduced the real estate for organic results. Finally, as voice search continues to increase, fewer users are going to Search Engines. It should come as no surprise then that we’re expecting organic clicks to continue to fall.” Joe Comotto, Operations Director.


“With GDPR dominating headlines last year, it is likely that something similar will hit the States. We’re already seeing the groundwork being laid down for this with California’s Consumer Privacy Act, but expect it to become more widespread.

Also, Amazon will continue to grow and improve their systems, becoming more accessible to advertisers and agencies in the long run.

Finally, on-demand streaming/content services will continue to grow, leading to increased price competition and potentially new opportunities for advertising on these platforms as they struggle to remain competitive.” – Craig Brown, Account Director.

Featured Guest

“As voice-activated devices become more prevalent, the core providers will develop a costing model for advertisers to finally include voice search on plans. AR will also be a new market for advertisers to tap into. We’ve seen the clearest application of this through retailer sites such as ASOS, allowing users to see apparel contextually. As this continues to mature, many will be lining up to explore this innovative new form of advertising.” – Max Trifonovs, Display Consultant, DQ&A.


From what it means to be an agency, to the future of voice, to big disruption in the Search space, we’ll be keeping an eye on these trends over the coming months. Which of our predictions do you agree with? Let us know on our social channels!


NMPi Predicts The World Cup Using Machine Learning: Man vs. Octopus vs. Machine

It was a trip to the grocery store one Sunday evening in May that I first saw it, The World Cup 2018 Panini Sticker Book. Unmatched in its dual role of footballing holy grail and financial black hole. With a quick glance over the shoulder to make sure no one was looking, I placed it delicately into my basket. After all, such a guilty pleasure required some degree of secrecy to ensure the maintenance of dignity.

Since then it’s all got a little out of hand really. My flatmates and I are fifty stickers away from completing the book – 650 in total. The team at the local Co-op know us by name – I’m now greeted with, ‘the usual, Alex?’, as I walk in.

To the utter bewilderment of those around me, the World Cup and its advertising machine has gone fishing and managed to catch a whale. I am that whale. But rather than let that get to me, I’ve decided to apply my enthusiasm in a slightly more useful way.

About a year ago we wrote a blog article predicting the results of the UK election, correctly arriving at the verdict of a hung parliament. So, we have decided to revive our predictive capabilities for the World Cup.

Fred Maude, the genius behind our previous efforts, has been busy hoarding reams of player data to apply to his new footballing-based algorithm.

We’ve incorporated machine learning into our business in a variety of different ways (award-winning in some cases), and Fred has been at the forefront of that movement. It works for our Google Shopping campaigns. It worked in 2017’s UK election. Will it work for Russia 2018? A few words from him later, along with his results.

But first, we thought we’d up the stakes a little. Alongside Fred’s machine, we’ve asked two very different figures to put their theories forward. After all, who wants machines to win every time? We all know how that ends…

Man – Max Flajsner, Head of Performance

Ignoring the fact Max is a Spurs fan, and so has little hope of being able to identify the characteristics of a successful team, we thought we’d let him have a go anyway. With a solid footballing background and a leading role in my sticker book efforts, he is perfectly placed to represent all of humanity.

In explaining his approach, Max revealed “my strategy mainly rested on Mousa Dembele. I just love him. So, to hear he won’t be starting had a huge impact on my decision-making. Belgium out in the quarters, Germany to ruthlessly defend their title.” Bless him.

Image Source: Sky Sports

2nd Round – Colombia v England, Uruguay v Portugal, France v Croatia, Brazil v Mexico, Belgium v Poland, Spain v Egypt, Argentina v Peru, Germany v Costa Rica

Q’ Finals – England v Germany, Portugal v France, Brazil v Belgium, Spain v Argentina

S’ Finals – Germany v Spain, Brazil v France

Final – Germany v Brazil

Winners – Germany

Octopus – Unnamed, Long Suffering Girlfriend

8 years ago, Paul the Octopus shot to fame by successfully predicting the results of the 2010 World Cup. Unfortunately, one thing I’ve learnt in this endeavour is that there are very few publicly accessible predictive octopi left.

So I turned to my cat (Pablo), perhaps the most single-minded creature I have ever come across, which I respect immensely. Whatever we tried, he did not want to participate in our ‘pick a flag with some tuna on it’ game. As he sat there staring at me, his eyes questioning how on earth it had come to this, I knew I had to find another way.

My final option was to go for a creature who matched Paul & Pablo in sporting awareness, though perhaps not in the number of legs. She has two legs, cares very little for football, is awesome, and just so happens to be my girlfriend. Upon being asked about her predictive strategy for this year’s tournament, she replied, “if I’m completely honest Alex, I just want this all to be over.” Perfect.

After some negotiations around where I would buy dinner, I managed to eek out an infographic. My goodness, I hope she’s right.

Image Source: Sky Sports

 2nd Round – Colombia v England, Uruguay v Portugal, France v Argentina, Brazil v South Korea, Belgium v Japan, Spain v Russia, Nigeria v Denmark, Germany v Costa Rica

Q’Finals – Germany v England, Portugal v Argentina, Brazil v Belgium, Spain v Nigeria

S’Finals – England v Spain, Portugal v Brazil

Final – Spain v Portugal

Winners – Spain

Machine – Fred Maude, Performance Manager

Finally, the one we’ve all been waiting for. Get your betting apps at the ready, because this one’s the winner. Here’s Fred…

‘The algorithm was designed to account for individual player performance over the last 12 months, along with national team form and results. This included a penalty bot should a knock-out game end in a draw.’

With Croatia and Morocco in the semi-final, and Argentina not making it out of their group, Fred’s machine has put its neck on the line. However, if he is right, we’re in for one hell of a tournament.

Image Source: Sky Sports

2nd Round – Senegal v England, Russia v Morocco, France v Nigeria, Brazil v Sweden, Belgium v Poland, Spain v Uruguay, Croatia v Australia, Germany v Costa Rica

Q’Finals – Germany v Senegal, Morocco v Nigeria, Brazil v Belgium, Spain v Croatia

S’Finals – Germany v Croatia, Brazil v Morocco

Final – Germany vs Brazil

Winner – Brazil

“I’m confident my predictions won’t be far off and my methodology is sound.’

“Initially, the aim was to develop a technique that was devoid of statistical and human bias. We could have gone away and taken stats upon stats to thread into our Machine Learning algorithm, however, we would essentially be feeding the machine with stats that hold no relevance for the game in hand. As everyone knows, it is not beyond Man City to be beaten by Stoke, although player statistics would not point you there. Thus, to remove any bias, and allow the machine itself to learn and make assumptions and stats for itself, we chose a different method.’

“This method involved taking the team line ups and results from over 5000 games in the last 12 months and then feeding this data into our classifier. My first experiments involved using the standard decision tree classifier, however, it was clear that the results were marred with inconsistencies. The decision to drop this and adopt the random forest technique was recently validated by an MIT Machine Learning algorithm aimed at the same outcome as ours.’

“To test the success rate, we looked at previous games with known results and supplied the algorithm with only the team’s line up data. Using this data, the machine then made a decision based on what it thought the result would be. We were then able to match these against the real results. My tests logged a success rate of 64%. Considering the volatility of football, as I am sure anyone who watches the game understands, we considered this as a sign of success.’

“Now that everything had been tested to our satisfaction we could finally predict the winners of The World Cup 2018. The only input data for prediction being the expected line ups of each World Cup team. Unfortunately for those die-hard England fans, a game against Senegal in the round of 16 may prove all too much.”


And there you have it. Tune in in 6 weeks’ time to see who triumphed in what Netflix is already touting as its next feature film – Man vs. Octopus vs. Machine.