Use AI for Better Attribution Modeling

Use AI for Better Attribution Modeling

In digital marketing, it is sometimes difficult to understand what touch-points and marketing investments contributed to a conversion. This is where attribution modeling comes into the picture, and there are now tools that use artificial intelligence and machine learning to improve the attribution modeling.

CUBED is one such attribution platform, and they work with enterprise organisations to show them the true value in a multi-channel, multi-device world, from impression through to site visit. Ultimately this ends in revenue driving conversions.

I had a discussion with Russell McAthy, CEO of CUBED. He has worked in a variety of roles within digital marketing, from in-house, to agency as well as consultancy –  with a consistent focus on data.

Now, over to the interview!

Russell headshot blue

Russell McAthy, CEO of Cubed

What is Your Company’s Background?

The underlying tracking technology that CUBED is built on was developed for a single client. Two years ago we turned that tracking and attribution element into a platform designed to answer many of  the questions that the industry at the time was struggling with. From my experience as a consultant prior to being CEO,  there were a number of barriers to entry for many organisations that were consistently coming up.

During the build of the company we have overcome a number of these barriers; such as onboarding time, time to insight, value of an impression and removing the ‘black box’ from an attribution conversation. We continue working on the connection between the insight and the action, and combined with building a scalable product, the important thing is that the industry as a whole starts to value an attributed view of the world. This enables brands to invest in areas that truly add value to their consumers and ultimately drive incrementality in business growth.

What Problem Does Cubed Solve?

The money spent by brands today does not generate the revenue that they make today; we show businesses what truly impacts their bottom line across the full consumer journey.

What Does Cubed do, and why is it Important to Your Customers?

CUBED is a Marketing Analytics platform that helps businesses understand the performance of the full consumer journey – multi-visit and multi-device. It can be used as a single platform of truth, a place for all marketing channels and external data to pulled into the same place to help inform the true story of how they impact revenue and value.

The CUBED algorithm means a shift from a last interaction/click world and into an attributed space. This allows smarter decision making  with the ability to look at how activity truly impacts consumers as they are acquired, research and hopefully ultimately purchase.

cubed-attribution-modeling

CUBED works with brands in all sectors processing billions of datapoint connecting impressions, emails, web visits and even retail store sales data.

Some of the ways we stand out from competitors is that we are independent and therefore we are not financially incentivised to make a company spend more money (especially in PPC and display) therefore our calculations are based on actual performance not something that will increase your PPC Spend.

Secondly we accept all data and store it – but the company owns it. There is full access to the raw data at any time. We can integrate with the current tech stack allowing all datasets to be included – not just the ones that google allows you to access.

How Does Cubed use AI?

Due to CUBED capturing every single data point, so every interaction between the consumer and the brand, we are able to use machine learning to train an algorithmic attribution model to best understand the individual touch points impacting consumers in order to drive success through digital properties.

The basic explanation of this is that we use a linear regression model, in which we look at the success events (conversions). The algorithm will go through every single touch point that has happened prior to a successful conversion and train on the most impactful elements.

We do this by taking into consideration a number of key factors on website pages; events that are triggered by the user as they engage marketing activities, including keywords, ads, and ultimately impression led activity when users view creative on external websites.

The key to this level of granularity we have available which enables the marketers within a silo to make tactical adjustments to improve performance all the way up to larger business goals, essentially meaning strategic shifts in budget, time and effort to hit key topline objectives.

In Your Mind, What is the Future of AI in Business and Marketing?

Firstly, there is a reason why I haven’t mentioned AI in our explanation of what we do at CUBED. Instead of artificial intelligence, we deliberately have used attribution intelligence, as we are currently in a world of artificial learning where humans are still integral to the role- and I don’t see that changing in the next 20 years.

The thing that will improve is the gap between data insight to action and the level of complexity as well as ultimately smartness of the learnings that we will receive from data at scale.

We will see an increase in  business shift to focus on algorithms, machine learning, artificial learning. However, we need to heed the learnings already made with big data, where the goal needs to be drive around the action and not just the capturing of incremental data points.

Businesses should define a clear strategy with objectives for any project that is utilizing these methodologies, otherwise, the value of these actions will not correspond with business growth.

Do You Think Marketers Will be Replaced by AI Robots?

No.

True marketers will not be replaced because the value of a marketer includes intelligence of consumer value to a brand. What will happen is that the methodologies behind algorithms and machine learning will remove some of the tasks which are undertaken by marketers currently at a scale which is only good for the industry.

True talent will shine through and will utilise the technology to drive significant value for organisations, as the tech is an enabler for decision making using data to provide smarter insights and actions.

The core goal for businesses is to understand where investments need to be made, not just in technology but also in people where we will see a shift in skill sets required to capture, manage, process and build the datasets but more importantly there is a significant shortage right now of true analysts and data driven marketers who can utilise everything that will become available to them in this new world successfully.

We just have to look at other industries to see how monotonous repetitive tasks have been replaced, opening up new careers, though not necessarily to the individuals that have been replaced.

Although terrible on an individual level, people who currently are employed to do what are repetitive tasks have an opportunity to invest their own time in becoming valuable to their organisation or others by seeing the writing on the wall. However, that has to be a personal decision for development as organisations will make a money based decisions on where they can get the best value.

In this interview, Russell McAthy provided fascinating insights into how artificial intelligence can be used for attribution modeling, multi-channel and multi-device. I think marketing departments will increasingly use tools like this to improve the ROI of their customer journeys.

unemyr_linkedin_horizontal_eng

I am an author, speaker and consultant in marketing automation and artificial intelligence.

Do you need help with marketing automation or AI-based solutions? Contact me and let’s discuss how I can help you!

Join my newsletter and get free eBooks and other content!

3dfinalsmall

Subscribe to my email list to get free eBooks - including Mastering Online Marketing - and information on marketing, marketing with AI and other marketing technology, as well as related topics.

Occasionally I might also send product offers or marketing information related to my business. Read the Privacy policy here.

We won't send you spam or sell your data. Unsubscribe at any time. For GDPR privacy information, visit the Privacy policy page linked to the left. Powered by ConvertKit

Author, speaker and consultant in the aras of marketing automation, artificial intelligence, and the Internet-Of-Things. Contact me if you need help!

2018-05-11T06:55:22+00:00 By |Artificial intelligence|0 Comments