Machine Learning + Causal Inference
OutPoint’s machine learning models rely upon causal inference methodologies. Causal inference is the process of determining the independent, estimated lift from spending on a particular channel that is a component of a larger cross-channel portfolio. We specifically use causal inference to derive incremental lift signals from both variations in spend and variations in revenue across channels over time.
OutPoint only needs a limited set of signals to make the models actionable, and once we have enough of these signals, we can infer the estimated efficiency of each channel, allowing us to construct an estimated return curve for each outlet. Since our models rely on inferred "cause and effect" vs click-based attribution alone, OutPoint media mix modelling (MMM) can capture the value of economic lift from less-attributable media such as Influencers, TV, and Radio, which do not always provide impression or click data at a per user level.
While MMM as a general methodology does not require granular click data, OutPoint's models will in some cases incorporate first & last click data as an input improving modelled inference around cause and effect.
Why Is This Important?
It is OutPoint’s goal to apply MMM to determine how much “incremental lift” each marketing channel is contributing to revenue, and thus how much to spend on each channel.✔️
Cross Channel Effects
MMM can clearly estimate cross channel effects across a marketing portfolio. The user can infer how much a single channel may be indirectly supporting the effectiveness of other channels within the mix.
Models can predict at which spend levels users will see an increase in customer acquisition cost (CAC). Being aware of the rate at which marketers are seeing diminishing returns will show optimal spend levels for profitability.
External Factor Impact
MMMs are being designed to account for external factors such as seasonality and pricing, showing a clearer picture of what is happing beyond average metrics.
The OutPoint Process
The process we follow aims to help answer the question, "How do I allocate my ad spend efficiently across channels?" The final result creates a future roadmap on how you can improve performance on every dollar spent.
The "Open Secret"
Scaled B2Cs like Wayfair, Netflix, and Amazon have already been investing heavily in the above areas and the concepts behind MMM. OutPoint’s thesis is to make these types of approaches accessible to all to help level the playing field and give growth stage companies the tools they need to enter their competitive landscapes. Google and Facebook have gone so far as to publish open-source code on the methodologies of incrementality and MMM, making similar models available to help marketers build their own tools.
Limitations of MMM
Currently, there are some limitations surrounding MMM. There is a constraint around the granular user level attribution. For example, one can use MMM to infer that a particular level in television spend likely drove a specific dollar amount in incremental revenue, but not the specific incremental user. Some business environments also deal with an extended purchase journey or a lot of noise in the buying process. In these situations, arguments can be made about distinguishing between causation and correlation.
More Information On Incrementality + MMM
- Netflix Research: Incrementality & Attribution
- Greylock: Building and Measuring Sustainable Growth Marketing
- Harvard Business Review: Marketing Analytics 2.0
- Mobile Dev Memo: Media Mix Models are the Future of Mobile Advertising
- Google Research: Challenges and Opportunities in Media Mix Modelling
OutPoint is a suite of data science tools used by high-growth B2C marketers to allocate paid media budgets optimized for incremental lift and improved marginal returns.
Contact us to schedule a demo or meet with the OutPoint team to learn how you can use MMM to lift your business.
🚀Sign up, or email firstname.lastname@example.org if you are interested in learning more.