Marketing Mix Modeling (MMM) – Optimize your Marketing ROI

Unpacking the granularity problem in MMM

One of the complaints many have with respect to MMM is that it does not provide granular insights. While there are multiple solutions to this problem (will talk about this in future posts), let me unpack the granularity problem. So what is the Granularity problem? Lets take the example of TV. Many brands spends lot of money on TV ads and the below are typical scenarios: Scenario 1 – different ads/creatives run concurrently. Scenario 2 – the ads/creative run at different cadence across the whole time period. The latter leads to data sparsity and often warrants use of cumulative TV spends/GRPs at the model level. The usage of cumulative spends

What? MMM has inbuilt Incrementality testing?

Did you know MMM has inbuilt Incrementality testing? Let me elaborate. Incrementality is defined as the additional impact of a marketing on the KPI (sales, TOMA, CAC etc..) over and above what would have been generated organically. Recently, we had an interesting conversation with a brand that ventured into TV ads since past one year. We learned that they want to measure the effect of TV ads along with the digital ads which they have been running since the brand’s inception. We suggested the brand that MMM not only gives a better way to find effectiveness of TV vis-a-vis digital ads, but also inherently tells you how much base/organic sales

How to deliver robust MMM models quickly

There are some parallels between efficient and quick MMM delivery and that of a F1 pit stop. Much like a F1 Pit stop, a lot of things needs to come together for an efficient and quick MMM delivery. They are: ◾ Data Analysis Skills: One of the biggest roadblock I have seen in getting MMM projects started in my 10 years of experience is data related problems. Many a time the project gets stalled or deadlines overrun for the sheer fact that some data anomalies were found once the models were built. It is imperative to do a thorough data check before commencing modeling and report back to the client

Boost your incrementality testing through Causal Experiments

During the Black Friday – Cyber Monday (BFCM) period, we often notice that brands increase their marketing spends, roll out discounts, try new media channels and launch new campaigns. The resultant sales for some of these brands during this period is higher than any other period in the year. But most marketers still don’t have a clear view on how to correctly attribute the incremental sales to the changes made during the BFCM. Identifying and attributing the incremental sales is crucial because the knowledge gained could be useful for future media planning and optimization. So is there a solution? Yes, The solution is Difference in Difference (DID) Method. Difference in

You can do MMM with small marketing spends

MMM is for enterprises of all sizes. Of late I came across a lot of posts proclaiming that MMM is not ideal for SMBs. I want to dispel some myths on this. 📌Small Marketing Spends Small marketing spends is not a show stopper. Not statistically and not marketing wise either. There are various statistical techniques that can accurately compute the effect size no matter the small marketing spends. 📌The Learning Curve The other major reason cited by people to dissuade SMBs from adopting MMM is the steep learning curve. Granted there is some learning curve in MMM but it is not steep. Many ask us, “why we keep sharing posts

Why Heteroscedasticity matters in Marketing Mix Modeling

MMM is something that always leads you to reminisce about the learning one had or hadn’t during their statistics course. 15 years ago, when I was a student, I attended one statistics seminar. In it the professor told “Always be testing your assumptions”. That statement rings true even now, especially in MMM. In MMM, inference is the name of the game. In inference, one deeply cares about the preciseness and un-biasedness of the regression coefficients. So the question arises, what can throw a spanner at your inference? Heteroscedasticity is one of the culprits. 📌 But what exactly is Heteroscedasticity? Can you simply eye ball it from your data? One of

MMM pro tip: Use spends instead of Impressions

1. Spends are more actionable and transactional, as you can measure direct impact on sales. Spends data directly reflects the financial investment in marketing (your CFO would be happy 😅). 2. Spends are more accurate than impressions. 3. Cross-Channel Comparisons Spend data enables easier comparisons between different marketing channels or campaigns in terms of their cost-effectiveness. This is essential for understanding where to allocate resources for maximum impact. 4. Saturation Curves Saturation Curves with spends give a clear indication of saturation of the medium rather than impressions.

Halo Effect ≠ Interaction Effect

In Marketing Mix Modeling, I often come across explanations that conflate Halo effect and Interaction effect. The two are not the same !! 📌 So what is Halo Effect? Halo effect is the positive ‘rub-off’ effect of a larger brand on its sister brands or products. This rub-off effect means that the customer buys the sister brand /product just because they have had positive experiences with the larger brand. These positive experiences in turn results in formation of trust and good will. It is this trust & good will which is then extended to the sister brand/s (which may or may not be in the same category as the larger

Market Mix Modeling (MMM) -101

Market Mix Modeling (MMM) is a technique which helps in quantifying the impact of several marketing inputs on sales or Market Share. The purpose of using MMM is to understand how much each marketing input contributes to sales, and how much to spend on each marketing input. MMM helps in the ascertaining the effectiveness of each marketing input in terms of Return on Investment. In other words, a marketing input with higher return on Investment (ROI) is more effective as a medium than a marketing input with a lower ROI. MMM uses the Regression technique and the analysis performed through Regression is further used for extracting key information/insights. In this

Market Mix Modeling 101 — Part 2 (Contribution Charts)

In this article, I would like to explain — How to interpret Contribution charts and what are the common pitfalls to avoid. So, what is a Contribution Chart? Contribution Chart is a visual way of representing what marketing inputs drive sales and how much is the impact of each marketing input. It always helps to ease the cognitive burden off your time-starved clients by representing market reality in a visual way. Types of contributing charts: Contribution charts are usually plotted in two ways: 1. Absolute contributions summing up to 100 2. Non absolute contributions summing up to 100 1 .Absolute contributions summing up to

Blogs