Marketing mix modeling made easy: An introduction to Cassandra
Learn how to carry out marketing mix modeling with Cassandra. Ideal for entrepreneurs and start-ups...
9 min read
Executives have always dreamed of a "single source of truth" to measure marketing performance and avoid wasting advertising budgets. Then came the wake-up call with iOS14, when Apple allowed users to disable tracking. In the post-iOS14 era, marketing attribution is about combining methods to calibrate your business model so you know which levers drive performance and make growth targets achievable.
In this article, I'll share insights and experiences from my Marketing Mix Modeling Service.
Table of Contents
- What is Marketing Mix Modeling?
- Why Marketing Mix Modeling?
- And what about Google Analytics 4?
- The Challenges of Marketing Mix Modeling
- What are the Implementation Options?
- What the New MMM-SaaS Solutions Can Do
- Disadvantages of Lightweight MMM and Robyn MMM
- Hybrid Attribution and Triangulation as Paths to the Future
- Frequently Asked Questions about Marketing Mix Modeling
What is Marketing Mix Modeling?
Marketing mix modelling (MMM) allows you to measure the results of your marketing and advertising campaigns and determine how different channels contribute to your goal (e.g., sales) based on econometric models of your historical data.
Marketing mix modelling is an established approach that was used and optimized by media companies long before digital marketing. However, as you can guess, this was manual, time-consuming, and therefore cost-intensive manual work. Even today, it is usually still agencies that collect data over long periods and convert it into models.
This breaks down the business metrics to distinguish between the contributions of marketing and promotional activities (incremental factors) and other factors (base factors). These factors that influence the marketing mix can be defined as follows:
- Incremental factors: Business results achieved through marketing activities such as TV and print ads, digital editions, price discounts, promotions, etc.
- Base driver: The base result is achieved without any advertising. It is due to the brand equity built up over years. Base results are usually fixed unless there are economic or environmental changes. Seasonality and other non-market factors such as GDP, growth rate, and consumer sentiment can also be subsumed under this.
- Other drivers: These are a sub-component of the base factors and are measured as the brand equity accumulated over a period due to the long-term impact of marketing activities.
Statistical analysis in media mix modelling uses multi-linear regression to determine the relationship between the dependent variable, e.g., sales or engagement, and the independent variables, e.g., advertising spend in the different channels.
For companies using marketing mix modelling, it is important to be critical in selecting the data they want to measure and the data they can measure. Data quality cannot be neglected, so companies need to spend time aggregating and cleaning data from internal databases, third-party sources, or both. Media mix models often use two to three years of data, allowing for factors such as seasonality.
Why Marketing Mix Modeling?
A picture speaks more than a thousand words:
(Source: Sellforte.)
Marketing Mix Modelling therefore enables the following:
1. Better allocation of marketing budgets
MMM can be used to identify the most appropriate marketing channel (e.g., TV, online, print, radio, etc.) to achieve marketing objectives and maximize returns.
2. Better implementation of advertising campaigns
MMM can be used to forecast optimal spending levels for the marketing channels used to avoid saturation.
3. Testing business scenarios
With Marketing Mix Modelling, business metrics can be forecasted based on planned marketing activities and various business scenarios can be simulated, such as increasing spending by 10% in period y or the amount of spending required to achieve a 10% increase in sales, etc.
Additionally, attribution models often overestimate the relative effectiveness of direct-response channels and underestimate the impact of brand-building media like TV. Despite this, TV remains the medium that generates the most incremental sales. Attribution models, however, struggle to measure the effects of media like TV.
Another reason digital attribution distorts ROI is that it is short-term. A study by Meta confirms that advertising effects can last months or years, with the majority of the payback coming from these long-term effects. Attribution models rarely look beyond a few days.
Moreover, the true definition of attribution is "cause and effect". Often, campaign planners assign credits to a social media campaign and call it "attribution":
But this is only a very small part of the marketing mix, and true attribution is the incremental effect of:
- Market research
- Product development
- Customer research and segmentation
- Mental and physical availability
- Price
- Distribution
- Marketing spend
- Competitive activity
- External factors (e.g., the state of the economy)
4. Better risk management
Since MMM uses historical data, you can identify the risks and dependencies of marketing activities.
5. Transparency and accountability
MMM is not based on click-based attribution models or testing methods but on econometrics, ensuring that the results are robust and objective.
But only a quarter of all advertisers are utlising Marketing Mix Modeling, as per DMA:
.png?width=1844&height=1101&name=output%20(25).png)
And what about Google Analytics 4?
Google Analytics 4 (GA4) is an improved version of Google Analytics that aims to better track user interactions across websites and apps. It allows for more flexible event tracking and integrates machine learning for better insights. However, GA4 has limitations in providing a holistic view of marketing performance:
- Limited historical data: GA4 can only provide data from the point it starts collecting, which may not be enough for comprehensive marketing mix analysis.
- Short-term focus: Like other attribution models, GA4 tends to focus on short-term interactions and may not accurately reflect the long-term effects of marketing activities.
- Data integration: While GA4 integrates well with Google Ads, it may not seamlessly integrate with other data sources or provide a complete picture of cross-channel marketing efforts.
In contrast, Marketing Mix Modeling offers a more comprehensive approach by analyzing a wider range of data and factors to measure the long-term impact of marketing activities.
The Challenges of Marketing Mix Modeling
Despite its advantages, MMM faces several challenges:
- Data quality: MMM relies heavily on the quality of historical data, which can be challenging to obtain and clean.
- Complexity: Building and maintaining accurate MMM models requires significant expertise and resources.
- Time-consuming: The process of collecting data, building models, and interpreting results can be time-consuming.
- Integration: Integrating MMM results with other marketing tools and systems can be complex and require additional effort.
Despite these challenges, the benefits of MMM in providing a holistic view of marketing performance often outweigh the difficulties involved.
What are the Implementation Options?
There are several ways to implement Marketing Mix Modeling:
- In-house: Building and managing MMM models internally requires expertise and resources but offers greater control over the process.
- Consulting firms: Engaging with consulting firms that specialize in MMM can provide expertise and support but may involve higher costs.
- SaaS solutions: Using SaaS platforms for MMM can offer convenience and scalability, though it may come with limitations in customization.
Choosing the right implementation option depends on the specific needs and resources of your organization.
What the New MMM-SaaS Solutions Can Do
New SaaS solutions for Marketing Mix Modeling offer several advantages:
- Ease of use: These platforms often come with user-friendly interfaces and pre-built models, making it easier for non-experts to use.
- Scalability: SaaS solutions can scale with your business, accommodating varying amounts of data and complexity.
- Integration: Many SaaS platforms offer integration with other marketing tools and data sources, providing a more comprehensive view of performance.
- Cost-effective: SaaS solutions can be more cost-effective than building and maintaining in-house models.
However, they may also have limitations in terms of customization and flexibility compared to bespoke models.
Disadvantages of Lightweight MMM and Robyn MMM
While lightweight MMM solutions like Robyn offer some benefits, they also have drawbacks:
- Limited depth: Lightweight models may not capture the full complexity of marketing activities and their impact.
- Reduced accuracy: Simplified models may lack the accuracy and robustness of more comprehensive approaches.
- Less customization: These solutions may offer limited customization options, making it challenging to tailor the model to specific needs.
It is important to weigh these disadvantages against the benefits when considering lightweight MMM solutions.
Hybrid Attribution and Triangulation as Paths to the Future
Hybrid attribution models combine elements of different attribution approaches, including MMM and digital attribution, to provide a more comprehensive view of marketing performance. Triangulation involves using multiple methods to validate and cross-check results, improving accuracy and reliability.
By integrating MMM with digital attribution and other methods, businesses can gain a more nuanced understanding of their marketing efforts and make more informed decisions.
Frequently Asked Questions about Marketing Mix Modeling
Q: How long does it take to implement MMM?
A: The time required for implementation varies depending on factors such as the complexity of the model and the quality of data. It can take several weeks to several months to build and deploy a comprehensive MMM model.
Q: How can I ensure data quality for MMM?
A: Ensuring data quality involves thorough data collection, cleaning, and validation processes. It is essential to use reliable data sources and regularly review and update the data used in the model.
Q: Can MMM be used for all types of businesses?
A: MMM is versatile and can be used across various industries and business sizes. However, the effectiveness of the model depends on the availability and quality of data and the specific marketing activities of the business.
Independent Consulting for Your Marketing Mix Modeling
As an independent consultant with extensive experience in Marketing Mix Modeling (MMM), I am here to help you take your marketing strategy to the next level. Whether you need assistance with the implementation of MMM solutions, support in selecting the right tool, or a customized analysis for your company – I offer expert advice and tailored solutions that are aligned with your specific needs.
Let's work together on your successful marketing strategy! Contact me today for a non-binding conversation to find out how I can assist you. Visit my contact page to learn more about the possibilities of working together. I look forward to your inquiry!
