Marketing Mix Modeling vs. Agent-Based Simulation

By John Pasinski, Jan 21, 2020

Marketing mix modeling and attribution is the marketing analytics industry go-to for understanding marketing's impact on business results. It has been used for decades and is trusted by many.  However, there are some that are realizing its limitations and exploring new modeling methods.  One alternative approach is market simulation - which blends agent-based modeling, behavioral economics, network science, attribution, and machine learning.  As a market simulation software company, we are often asked how market simulation compares to marketing mix modeling.

The Differences In Methodologies

While both can be used to reveal correlations between past marketing activity and business outcomes, the two methodologies are grounded in two very different scientific theories.

Marketing Mix Modeling is a statistical or deterministic approach that explains variation around some baseline value in a dependent variable (often times sales) due to marketing activities. A regression is constructed between time series of sales data and marketing to attempt to correlate changes in one to another. The model’s coefficients are calibrated to minimize the error between actual and modeled sales. The model is then applied to answer questions around marketing investment level and mix. 



One of the main scientific theories applied in market simulation is agent-based modeling, which is a probabilistic approach. Agent-based modeling takes a bottom-up approach to simulate how agents are likely to behave. Interdependent variables within the simulation recreate the dynamics of the market. Each sale in the simulation results from the action of an individual simulated agent. The initial conditions and parameters define how consumers behave, influence one another, make decisions, and interact with media.


The parameters of the simulation are adjusted to minimize error between actual and simulated sales. The calibration processes confirms that the simulation is an accurate representation of the world. Due to its probabilistic approach, market simulation has strong explanatory power, which enables users to go beyond attribution and run what-if scenarios - which often can achieve high levels accuracy.

A number of parallels between the two methodologies often create confusion about their similarity. Each has coefficients or parameters that are adjusted to minimize error in an attempt to better reflect reality. Each approach may be used to guide decisions on paid marketing investments. The key distinction is that marketing mix analyzes a single brand’s activity in aggregate, while market simulation recreates a brand’s marketplace based on individual consumer actions. The differences are summarized further below:




The Differences in Application

Marketing mix modeling is well-suited to answer questions related to the optimization of paid marketing investments.  However, this is only one component in a marketing strategy.  Market simulation allows teams to run analyses to optimize the four P’s of marketing by considering other factors beyond paid media, such as:

Interdependent KPIs:  Consider trade-offs between sales, perceptions, awareness and word-of-mouth.

Consumer segments:  Prioritize segments or identify how to personalize campaigns by segment.

Attributes driving choice:  Test creative messaging or understand how product features are influencing outcomes.

Competing alternatives:  Respond to competitive actions and/or optimize a portfolio.

Probabilistic outcomes: Assess risk based on a distribution of likely outcomes with a Monte Carlo analysis.

Market simulation provides the capability to answer a broader set of strategic questions about resource allocation. We have seen a number of cases where an analytics team initially uses market simulation to replace a marketing mix model, but quickly evolves into using it for a variety of other business needs, such as:

Product Development:  What product features should we prioritize for development?

Pricing and Promotion optimization:  What is the optimal pricing or promotions strategy?

Product Launch Strategy:  What is the right investment mix to successfully launch a product?

Customer Experience Optimization:  What parts of the customer journey should we focus on optimizing?

The best way to decide which approach is right for you is to ask yourself the following questions:

  • Do I want an in-house software solution?
  • Do I need paid media optimization or strategy optimization?
  • Do I need faster answers on a recurring basis?
  • Do I need to run predictive or what-if analyses?

If you answered yes to the above questions, market simulation may be the answer for you.


How Prescriptive Analytics Provides a Roadmap to Your Revenue Target

How a Flexible Approach to Modeling Benefits Businesses
Collaboration Between Data Scientists and Decision-makers? It's Possible.
5 Ways Unified Analytics Help Your Business