Next Generation of Marketing Mix Modeling

HamiltonAI is an AI-driven Marketing Analytics and Media Optimizations Platform. Once loaded with the right data HamiltonAI enables scalability in deployment of many models simultaneously and rapidly. Each model builds upon learnings from hundreds of previously developed models, contributing to the improvement of the general modeling framework.

By providing actionable key business insights, HamiltonAI empowers marketing professionals to drive business impact through accurately, compliantly and rapidly track, optimize and forecast marketing investments across all media channels.

Traditional Marketing Mix Modeling approach

The general problem of attributing effect to the activity that caused it, is inherently hard and requires sophisticated models to disentangle the dynamics behind the decisions of the masses. Traditional models based on linear regression:

  • Models every variable as independent
  • Impossible to detect cause and effect
  • Forces a linear interpretation of a non-linear world
  • Dependent on human interpretation
  • Takes time – outdated learnings

Blackwood Seven’s Method

Blackwood Seven’s modeling framework attacks this problem by isolating the dynamics across all media channels (offline and online) for the consumers. This enables us to quickly figure out how to allocate future budgets that leverage all possible knowledge across all channels in order to provide optimal profitability. 

  • Fits highly non-linear relationships and dynamics
  • True attribution through cause and effect
  • Automatically increases certainty
  • More robust/objective
  • Instantly analyze the present to predict the future

Hamilton AI is made for the real world
– in real time

Hamilton AI is able to bring marketing into a dynamic learning loop:

1) Firstly, in the process of reviewing previous media and marketing effects
2) Secondly, in the prediction of possible effects from various media investment scenarios
3) Thirdly, in the execution of media plans and evaluation of results 

When repeating these steps, the underlying model’s accuracy will naturally improve because of the platform’s machine learning capabilities.

This learning loop and probabilistic modeling is the foundation for Hamilton AI being adaptive at all times. Always taking into account changes such as e.g. new sales targets, increased competitor activity, or more currently the spread of COVID-19. Hamilton AI is made to be nimble to the real world. Not for the real world to be force fit into a model.

The modeling itself can actually be implemented in less than six weeks. When up and running, it not only predicts new outcomes to changes in key variables in a few hours. The model can also be repurposed in a couple of days for e.g. branding effects to topline growth – or a new response variable like e.g. customer churn.

Hamilton AI machine learning loop

Hamilton AI gets smarter all the time with continuous updates

Hamilton AI is built to consolidate marketing measurement

With HamiltonAI marketing investments are treated like financial investments

CMOs – and not least CFOs – have long desired a measurement model that could both identify and predict the business outcomes of marketing spending. 

Questions still linger like:

  • What are the exact marketing contributions to top-line growth or baseline sale?
  • What is the contribution per channel and touchpoint in the customer journey?
  • What is the optimal balance between sales tactics versus branding initiatives?
  • How should my marketing and media plan look like in terms of optimal spend?

Previously, these questions have been addressed in different ways by two different set of measurement practices, Marketing Mix Modeling (MMM) and Multi-Touch Attribution (MTA)

The Shortcomings of previous marketing measurement methods

The econometric Marketing Mix Modeling – typically estimating the sales effect of each media category and other factors – is not really suited for today’s marketing landscape. It’s too high-level. With a whole new swath of digital media publishers, more granularity is called for.

MMM also hides interdependencies between channels and touchpoints. It requires a large data volume. And being time-consuming and expensive, it is also quite infrequent in use.

After MMM, a more recent practice has been introduced. One which is more fitted to the digital media landscape, namely Multi-Touch Attribution. Unfortunately, this method uses cookies to track user response across digital media publishers. These third-party cookies are about to vanish due to Big Tech’s unwillingness to support them and GDPR. As a consequence, MTA will inevitably become severely incapacitated.

Total Marketing Modeling is the way forward

Imagine if you could build a more unified marketing measurement model for identifying the effects hierarchy throughout the customer journey. Both on- and offline – on a very granular level, down to individual media publishers. 

A model where you work your way down from attributing the effects of both paid media categories and other economic factors down to individual media publishers. The objective being to achieving an actionable plan that let you optimize marketing investments down to each touchpoint against either fixed budgets or set business targets. Hamilton AI first determines the contribution of each marketing and media investment using probabilistic modeling. Then it uses simulations to recommend the optimized media plan generating the best possible outcome.

With up to 99% accuracy the media plans recommended by Hamilton AI generate more than 15% business uplift from media effects – which we guarantee by the way!

The Hamilton AI modeling of media effects on sales revenue 

Hamilton generates a network model that connects all media spend – and other data like interest rates, pricing, distribution, competitive activity levels, weather – to the sales KPI. When the connections have been made, it’s possible to predict business outcomes from the media effect of different scenarios. All the way down to publisher level.

On the operational level the marketing or media manager will be able to select the optimal spend allocation between marketing channels and media publishers. Either from a sales target objective (how much do I need to spend) – or a budget constraint (how much can we sell).

Contact Us