April 29, 2026

How to Use MMM Without Historical Data: Alternative Data Sources and Techniques

By Gabriel Mohanna · 3 minute read

About the Author

Gabriel is Head of AI Strategy at ScanmarQED, bringing deep expertise across the full marketing measurement stack — MMM, multi-touch attribution, and incrementality experiments. He has spent his career translating complex models into decisions that CMOs and growth teams can actually act on, bridging the gap between data science rigour and business clarity. As the founder of MMM Labs — a SaaS platform built on leading open source frameworks like Robyn, PyMC-Marketing, and Meridian — he has been through the full arc of building and scaling a measurement product, which ScanmarQED acquired to accelerate its MMM offering. At ScanmarQED, Gabriel leads AI strategy company-wide — defining how AI transforms product, marketing, sales, and operations, and moving the organization from AI-curious to AI-native.

Data – we all want it, some have A LOT of it… others have very little.

So, what can you do when you're short on historical marketing data? No need to worry. Marketing Mix Modeling (MMM) can still be effective, even with limited data, by leveraging alternative data sources and advanced techniques. In this article, we’ll explore how you can build powerful models using proxy data, aggregated data, and other strategies, ensuring you still extract valuable insights for your marketing efforts.

Here are the key types of data that MMM can use when historical data is limited:

1. Aggregated Sales Data

Even if you don’t have a rich history of sales data, Marketing Mix Modeling can still work. Sales data, even in shorter time frames like weekly or monthly figures, can offer valuable insights. By combining this with external data sources, you can detect patterns and trends that help guide decision-making.

2. Marketing Spend Data

Even with limited historical data, your marketing spend data from various channels—TV, digital, and social media—can help inform the model. By knowing where your budget is allocated, MMM can establish relationships between spend and performance, even when you have minimal data available.

3. External Factors

MMM isn’t just about your internal data. You can incorporate external factors such as:

Seasonality: Sales trends vary across seasons, such as holidays, and this can be modeled even without extensive internal data.
Economic conditions: Data like consumer confidence, inflation, and unemployment rates can contextualize your sales performance.
Competitor activity: If you have data on competitors' promotions or ad campaigns, these can also be factored into the model.

4. Proxy Data

When historical data is absent, consider using proxy data. Industry benchmarks, publicly available data (such as consumer trends), or insights from similar businesses can serve as a solid starting point until you gather your own data. These sources could include:

Industry averages for marketing effectiveness
Consumer trends in your sector
Publicly available economic data

5. Expert Knowledge and Assumptions

When data is scarce, using expert assumptions is a practical way to make educated guesses about how your marketing activities should perform. These assumptions can be refined as you collect more data over time, making your MMM model increasingly accurate and actionable.

6. Experimental Data

Another method to overcome limited data is by running small marketing experiments, such as A/B testing or pilot campaigns. The results from these experiments can be input into the model, helping to quickly understand the effectiveness of different marketing channels.

7. First-Party Data from Digital Platforms

If historical sales data is unavailable, turn to your digital platforms. Metrics such as impressions, click-through rates (CTR), and conversion rates can be instrumental in building your MMM model—particularly when assessing the performance of your digital marketing efforts.

8. Publicly Available Data Sources

Use third-party or public data sources to supplement internal data. Some options include:

Google Trends: To help you understand consumer interests
Social media insights: Facebook and Twitter can give you a sense of brand awareness and engagement.
Government economic reports: Open data from the US Government can provide context for broader economic conditions that affect your business.

9. Short-Term Data Collection

Even if you’re just starting with MMM, using a few months of sales and marketing spend data can still yield useful insights. As time progresses and more data is collected, your model will become more robust, allowing for increasingly precise predictions.

10. Collaborate with Vendors or Agencies

If you work with media agencies or other vendors, they might have access to historical campaign performance data that can serve as a valuable input for your Marketing Mix Model. This helps fill gaps when your internal data is lacking.

Even if you don’t have a rich historical data set, Marketing Mix Modeling can still be effective by leveraging current aggregated data, proxy data, and external factors. Over time, as you collect more of your own data, your model will become more precise and actionable. By using these alternative approaches, you can gain valuable marketing insights and make data-driven decisions without waiting for years of data collection. MMM Labs can help you discover new data sources to help optimize your marketing.