The I-COM Data Science Hackathon is a 36-hour marathon, where competing teams develop algorithms using data science analytics to solve predictive modelling challenges on marketers’ datasets.
This year, it was hosted in the beautiful Cruise Terminal in Porto. Unilever and Intel provided the challenges for teams. The attending teams were a mix of academic data scientists (universities), analytics and marketing specialists (agencies).
The team from OMD EMEA took on the Intel challenge –
Business Challenge: What is the impact of discussions in social media and brand health indicators on advertising effectiveness for high consideration purchases such as consumer PC sales in the US?
Prediction Challenge: Predict the sales revenue by CPU brand/device brand combination by month for Jan and Feb 2017.
A sample of the data was provided by sponsors and Intel in advance of the Hackathon for teams to interrogate. The shared data included social (twitter volume), Millward Brown brand health survey data, search, ad spend and sales data.
To cover all aspects, OMD EMEA sent a team with a blended skill set to approach it. Our team included Paul Cuckoo (Global Channel Planning Manager), Harry Daniels (Analyst), Cate McVeigh (Head of Marketing Sciences, Intel team) and Adam Abu-Nab (Social Intelligence Exec Director).
The Hackathon –
The OMD EMEA team created a predictive sales estimator from a combination of MMM (marketing mix models) and data output to show how variable ad spend can affect revenue.
What worked: Consideration was most effective in predicting sales. The consideration data from Millward Brown was effective in allowing us to predict revenue. Consideration was shown to be a strong driver of revenue and we were able to isolate a strong December/Christmas trend.
What didn’t work: Twitter data effects. We weren’t able to truly isolate the effects of the twitter data on media effectiveness.
Finalist teams from Ebiquity and Analytic Partners also presented MMM solutions but instead used a nested approach. This approach carves out relationships with twitter/brand health and spend first, before nesting this in a final revenue model.
Interestingly, dashboard solutions were also presented as outputs. These dashboards could forecast spend required to meet revenue targets based on brand health/twitter indicators.
Our key takeaways –
Do your prep: Sample data prep is the secret ingredient to success for Hackathons. Teams which pre-formatted and did as much data prep work in advance of the hackathon freed up valuable time. This meant they had more time to spend on modelling their solutions, as well as conceptualising and visualising the story they wanted to tell.
A fuller data eco-system is needed for business application: A challenge for all teams was the limitations of the data sources provided. For there to be actual business applications, a fuller eco-system of data sources and metrics could be provided.
For example, a common problem teams faced was the search and social data provided (tweets) was solely volume over time and a mix of owned (brand driven) and earned (user) mentions within that. This limited data caused predictable peaks around owned campaign activity and campaign seasonality trends (Black Friday, Christmas, Apple Launches). This volume was also a mention and not the reach of a mention, which could prove a stronger correlation with ad effectiveness/intent/sales.
The semantics are equally important as the numbers: For social to be used as an indicator for purchase, you need to be able to cut where the real user discussion is happening and the richer semantics out of it. For example, are these mentions positive, negative, intent or consideration based? Can they be correlated and validated with intent/consideration survey data from Millward Brown? For search, what is the context in which people are searching for your brand, not just the volume?
At OMD EMEA, we have the capability to use tools that can cut social and search in these more meaningful ways. There’s also the differing audience discussion environments that need to be considered. A parallel test we ran using our social tools found that more Intel sales/intent discussions and social video views were happening on wider social platforms. For example, YouTube/twitch were platforms that resonated with gamers, while forums were preferred for B2B tech-heads in particular.
Given the nature of a hackathon, it’s understandable that the amount of data provided to teams is managed so that a solution can be turned around in 24 hours. What it has allowed teams to do is test some interesting ideas and models, take these and plug them into the broader data sets they have to work with during their day to day.
MMM still the most useful for marketers
Data science is an exciting field with new techniques that can revolutionise accurate predictions with minimal data. However, to properly answer business questions, regression modelling in the form of MMM has a long way to go before it’s beaten. Feeding that model with all the correct data sources is key to its accuracy.
Last week I headed to beautiful Lisbon for the 2016 IAB Interact Conference where the three-day agenda was packed with sessions covering the latest business and technology developments in video, mobile, programmatic, content creation, brand safety and media fragmentation.
For one of the sessions on Tuesday 12th May I took to the stage with Mohamed Eldjendoubi, Digital Manager for Renault AMI (Africa, Middle East and India) to discuss ‘The Mobile Imperative’. As we are by now aware, portable internet-connected devices are revolutionising the way people connect, whether that be with friends, information, entertainment or brands. This change in behaviour has caused many challenges for the marketing industry as brands and agencies come to terms with how best to engage in this increasingly mobile-first world. Based on these trends, Mohamed and I shone a light on the initiatives Renault has tested and adopted in order to cater to our rapidly evolving mobile-first industry – a transcript of our discussion is below.
AN: What made you realise that Renault had to change the marketing initiative being activated across the AMI region?
ME: Following a summary of audience behaviour research we realised that 50% of our audience is visiting Renault through mobile devices. The way in which consumer behaviour is changing means that they are now mobile-first so we needed to adapt, but at the time Renault didn’t have the infrastructure to cope with this.
AN: Could you describe how you went about making changes the existing marketing practices? What was the process and how easy was it to implement?
ME: There were many non-believers who I had to convince to try something new, so above all I had to convince them to be brave. This process involved simply showing the amount of digital time and internet access that is mobile. Once on board, we decided that our first step would be to create an Innovation and App Factory for the AMI region to reduce costs and delays and, most importantly, improve effectiveness and efficiency. The idea here was to bring a constant stream of new innovation into the marketing arena for Renault. This is geared towards helping us realise our ambition of being seen as an innovative brand, and also for us to understand how best to engage with mobile-first audiences. It took a brave marketer to achieve this and a brave company to say yes, but it was worth it.
AN: Could you provide an overview of the new initiatives that have been launched by Renault in AMI?
ME: For the launch of the KWID in India we developed an initiative that combined a mobile app which allows users to compare the new Renault KWID to other cars, see 360 views and book themselves a KWID test drive, in combination with a virtual showroom providing people with the chance to view the car online at a time that was most convenient to them. For the launch of the Kadjar, we launched an app for African and Middle Eastern countries, which was designed to provide users with the confidence to do more with their new off-road vehicle. The idea was to build a community of people who are going ‘off-road’ for the first time and using the app to allow Renault to maintain an on-going experience with them through their ownership lifetime.
AN: Could you provide some insight into the benefits Renault has seen from launching these initiatives?
ME: We’ve seen fantastic results including increased sales – 15% of all KWID sales in India came from people who had never physically seen the car. Metrics such as brand engagement, brand sentiment and motivated dealerships all increased. Visibility across our markets has dramatically improved, while sales boosts have been directly correlated to e-commerce and leads conversion.
AN: Would you say you behave as a mobile first advertiser? If so, can you provide your definition of what this term means for Renault?
ME: Yes Renault is definitely mobile-first. For us this means communicating with consumers via the mobile platform and making sure this is at the heart of our contact strategies, whether that be before, during or post the purchase process. This means ensuring our websites are mobilised and that the content works properly for both feature and smartphones. The content promoted on these devices has to be easy for them to access any content served must be relevant. This means we are no longer relying on traditional media channels to reach consumers, but a range of mobile-first channels to communicate social, search and display. We therefore place a focus on apps designed to make the Renault experience better for consumers, whether that be a car configuration app to allow them to customise and order their car or a companion app designed to help them understand all the buttons on their new car as well as introduce lifestyle content. This could be a My Renault app designed to alert them to serving, part recalls and general maintenance info. Our ethos is to deliver utility and ease of use to customers and, within the AMI markets, this means making that available on mobile devices, which is where the consumers are.
AN: Could you give us any insight into what’s coming next from Renault?
ME: At the moment we are working on having a Digital Lab within the AMI region to focus on developing and improving our mobile apps and innovations on a regional scale – a kind of App Factory where we can work with digital innovations such as NFC, Beacons and VR to enhance the customer experience. The Digital Lab will be the main lever for our Digital Acceleration Programme, ADAP.
AN: Do you have messages for other advertisers going through this journey? What should they focus on and how should they deal with mobile non-believers?
ME: My messaging would be as follows: make sure that you are sending the right message, at the right time, on the right device! As Google said, ‘fail fast or win fast’. We had a lot of non-believers in Renault but throughout this process they have been convinced when they saw mobile bookings figures. Driving the change is a daily job within our management but at the end of the day we truly believe it will breed success.