Marketing Mix Modeling

What is Marketing Mix Modeling?

In recent times, we have seen the proliferation of new media (Internet, viral marketing, event marketing, sports marketing, product placement, cell phones, etc.), decreased television viewership, the advent of TiVo and similar technology where viewers can skip through commercials, and increased cost-cutting pressures. All of this has combined to increase demands for marketing departments to maximize the return on their marketing investments; that is, to optimize the combination of marketing and advertising investments to generate the greatest sales growth and/or maximize profits. Marketing mix modeling measures the potential value of all marketing inputs and identifies marketing investments that are most likely to produce long-term revenue growth.

  Typically, marketing mix modeling involves the use of multiple regression techniques to help predict the optimal mix of marketing variables. Regression is based on a number of inputs (or independent variables) and how these relate to an outcome (or dependent variable) such as sales or profits. Once the model is built and validated, the input variables (advertising, promotion, etc.) can be manipulated to determine the net effect on a company’s sales or profits.
The data that go into creating a marketing mix model include:

• Economic data
• Industry data
• Category data
• Advertising data (including copy testing)
  • Promotional data
  • Competitive data
  • Service data

• Product data
  • Pricing data
  • Features & performance
• Market outcome data
  • Sales
  • Revenues
  • Profits

 

Marketing Mix Modeling Services

Decision Analyst is a leading international marketing research and analytical consulting firm with over 3 decades of experience in state-of-the-art modeling, simulation, and optimization. A team of Ph.D.'s heads up Decision Analyst’s advanced analytics work. They publish many white papers on advanced analytical methods and speak frequently at marketing research industry conferences.

Marketing mix modeling (MMM) is statistical analysis such as multivariate regressions on sales and marketing time series data to estimate the impact of various marketing tactics (marketing mix) on sales and then forecast the impact of future sets of tactics. It is often used to optimize advertising mix and promotional tactics with respect to sales revenue or profit.
The techniques were developed by econometricians and were first applied to consumer packaged goods, since manufacturers of those goods had access to good data on sales and marketing support. The first companies dedicated to the commercial development of MMM were MMA (then Media Marketing Assessment) started in 1990 and the Hudson River Group founded in 1989. Other early pioneer-users of econometric modeling were the ATG group at the advertising agency JWT in the 1990s and later incorporated into MindShare ATG, BrandScience at Omnicom, and the specialist modeling agency OHAL since the late 1980s. These agencies took MMM from being a little-used and academic discipline to being a widespread and common marketing tool. Improved availability of data, massively greater computing power, and the pressure to measure and optimize marketing spend has driven the explosion in popularity as a marketing tool. In the recent times MMM has found acceptance as a trustworthy marketing tool among the major consumer marketing companies. Often in the digital media context, MMM is referred to as attribution modeling.

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 article, I will talk about various concepts associated with understanding MMM.

1. Multi-Linear Regression:

As mentioned earlier, Market Mix Modeling uses the principle of Multi-Linear Regression. The dependent variable could be Sales or Market Share. The independent variables usually used are Distribution, price, TV spends, outdoor campaigns spends, newspaper and magazine spends, below the line promotional spends, and Consumer promotions information etc. Nowadays, Digital medium is highly used by some marketers to increase brand awareness. So, inputs like Digital spends, website visitors etc. can also be used as inputs for MMM.

An equation is formed between the dependent variables and predictors. This equation could be linear or non-linear depending on the relationship between the dependent variable and various marketing inputs. There are certain variables like TV advertisement which have a non-linear relationship with sales. This means that increase in TV GRP is not directly proportional to the increase in sales. I will discuss about this in more detail in the subsequent section.

The betas generated from Regression analysis, help in quantifying the impact of each of the inputs. Basically, the beta depicts that one unit increase in the input value would increase the sales/profit by Beta units keeping the other marketing inputs constant.

Sales Equation

2. Linear and Non-Linear Impact of predictors:

Certain variables show a linear relationship with Sales. This means as we increase these inputs, sales will keep on increasing. But variables like TV GRP do not have a linear impact on sales. Increase in TV GRPs will increase sales only to a certain extent. Once that saturation point is reached, every incremental unit of GRP would have a less impact on sales. So, some transformations are done on such non-linear variables to include them in linear models.

TV GRP is considered as a non-linear variable because, according to marketers an advertisement will create awareness among customers to only a certain extent. Beyond a certain point, increased exposure to advertisement would not create any further incremental awareness among customers as they are already aware of the brand.

So to consider TV GRP as one of the modeling inputs, it is transformed into adstock.

TV Adstock has two components.

a. Diminishing Returns: The underlying principle for TV advertisement is that the exposure to TV ads create awareness to a certain extent in the customers’ minds. Beyond that, the impact of exposure to ads starts diminishing over time. Each incremental amount of GRP would have a lower effect on Sales or awareness. So, the sales generated from incremental GRP start to diminish and become constant. This effect can be seen in the above graph, where the relationship between TV GRP and sales in non-linear. This type of relationship is captured by taking exponential or log of GRP.

b. Carry over effect or Decay Effect: The impact of past advertisement on present sales is known as Carry over effect. A small component termed as lambda is multiplied with the past month GRP value. This component is also known as Decay effect as the impact of previous months’ advertisement decays over time.

3. Base Sales and Incremental Sales:

In Market Mix Modeling sales are divided into 2 components:

a. Base Sales: Base Sales is what marketers get if they do not do any advertisement. It is sales due to brand equity built over the years. Base Sales are usually fixed unless there is some change in economic or environmental factors.

b. Incremental Sales: Sales generated by marketing activities like TV advertisement, print advertisement, and digital spends, promotions etc. Total incremental sales is split into sales from each input to calculate contribution to total sales.

4. Contribution Charts:

Contribution charts are the easiest way to represent sales due to each marketing input. Contribution from each marketing input is product of its beta coefficient and input value.

E.g.: Contribution from Newspaper = β* Newspaper Spends

To compute contribution %, contribution due to each input is divided by the total contribution. I will elaborate on the interpretation of contribution charts in MMM 101 part 2.

5. Deep Dives

MMM results can be used further to perform deep dive analysis. Deep Dives can be used to assess the effectiveness of each campaign by understanding which campaigns or creatives work better than the other ones. It can be used to do a copy analysis of creatives by genre, language, channel etc.

Insights from Deep Dives are considered for Budget optimization. Money is shifted from low performing channels or genres to high performing channels/genres to increase overall sales or market share.

6. Budget Optimization

For any business, Budget optimization is one of the key decisions to be taken for planning purposes.

MMM assists marketers in optimizing future spends and maximizing effectiveness. Using MMM approach, it is established that which mediums are working better than the other ones. Then, budget allocation is done, by shifting money from low ROI mediums to high ROI mediums thus maximizing sales while keeping the budget constant.

So folks, this was a brief about Market Mix Modeling. Stay tuned for more articles on MMM.

By applying a more holistic, commercially-focused approach to marketing mix modeling, marketing driven analytic organizations can get a much more accurate read on the ROI of their marketing investments. Applying fact-based marketing mix ROI optimization solutions to marketing investments can drive 40% improvements in your marketing effectiveness.

Marketing ROI is top of mind for senior executives across every industry and global market. As the adoption of marketing mix modeling and marketing ROI measurement has grown, so has the need for increased speed, granularity and holistic business reporting. The practice of marketing mix modeling has now evolved into commercial effectiveness for many companies. Commercial Effectiveness encompasses a much broader and relevant data set and helps establish investment synergies that provide a considerably more accurate attribution of ROIs. This exciting and dynamic evolution has been enabled by advances in data, technology and innovative analytics.  It has broadened the scope of the analysis to include marketing, operations and external factors as well as dramatically improving the speed-to-insight.  As a result the combination of richer insights delivered faster supports better alignment with business planning processes.  In addition, these granular models are able to support tactical marketing optimization in a way that aligns with core business processes. As the models have evolved, cross-functional involvement has expanded and the value delivered through this work in the form of increases in sales, profit and shareholder value has increased dramatically.

MMA is enabling companies to address critical business questions, including:

• What is the offline and online impact from traditional, digital and social media and sales? What is the ROI for each channel and campaign?
• What would be the future impact of a change in the marketing strategy and budget?
• What is the optimal spend and mix of marketing investments
  to achieve financial objectives?
• How to balance investments in brand building vs. product focused marketing?
• How to optimize investments to drive sales and profit by customer segment?
• How does marketing perform in-season vs. out of season? What is the optimal timing and execution?
• What is the impact of brand equity, consumer sentiment and customer satisfaction on sales?
• How to optimize the value of a loyalty program?
• What is the optimal sequence of activities to drive customer behavior (Next Best Action)?
• How does marketing effectiveness vary by response channel and geography?
• How to optimize the effectiveness of each marketing channel by sub-channel, campaign, geography, timing, audience/target, duration and publisher to improve ROI?
• What is the appropriate cross-media attribution (e.g. TV driving Search)? How to take advantage of media synergies? What is the role of paid, earned and owned media?
• What is the impact of operations factors and external factors (macroeconomic, weather, competition, etc.)?

Delivering value to our clients requires four key ingredients:

1. Holistic, More Accurate Marketing Mix Models – The marketing mix analysis within the environment of a commercial effectiveness model produces an approach that simultaneously measures the impact of all business drivers including traditional media, digital media, operations factors, consumer attitudes and external factors on offline sales and online sales at the level in which they are executed and by customer segment. Because commercial effectiveness models incorporate potential synergies and attributions on marketing variables from sales, operations, product, external and other important areas, the models do not over or under attribute success to variables.

2. Integration of Digital Attribution and Customer Data
   By integrating the two holistic sets of capabilities marketers gain an accurate, actionable view of “Full Attribution” enabling both top-down and bottom-up marketing optimization to drive gains in marketing performance (incremental revenue and profit driven by marketing) in the range of 20-30%. When reviewing a marketing ROI metric at the total marketing channel level (e.g. total online video), it is important to consider that such a metric is the aggregate of many individual and granular ROIs at a very tactical level that vary by campaign/creative, timing, placement/publisher, duration, market and audience. Optimizing at this tactical level represents a meaningful opportunity to improve the ROI of each channel, while driving measurable increases in the sales and profit driven in each marketing channel. Doing this requires a purposeful integration between the marketing mix models, data from a DMP and/or On-boarder, digital attribution platform and a method for driving activation through media planners either through a manual process or a direct link into planning tools or the current DSP.

3. Speed to Insight
   Embedding holistic commercial effectiveness/marketing mix analytic capabilities into ongoing business planning processes in order to produce high-value results requires the insights be activated and leveraged quickly. Historically it’s taken months to produce and deliver the statistical models necessary to activate the results.  Through dramatic enhancements in data automation, technology and modeling platforms the capability to rapidly produce thousands of  client-specific predictive models to test combinations of business variables at a very granular level, companies have been able to reduce speed-to-insight timing to coincide with key business planning and measurement initiatives.

4. Consulting and Change Management
   Changing and transforming age old processes can be challenging.  However when effective change management and assimilation steps are implemented the path to unlocking multi-million dollar gains can be opened.  Marketers and CFOs are looking for a unified approach to tap into that value that aligns to their decision-making ability and business planning cycles – usually quarterly, often monthly, and sometimes even weekly. This needs to come from integrating modeling and attribution platforms with experienced transformation-focused consulting that helps an organization leverage what’s working best while guiding them to assimilate new learnings and advantages to win going forward. MMA works closely and collaboratively to help clients combine the best of what’s worked and what they need to have to win going forward to shape competitively advantaged business strategies.

 lthough some have termed 2016 the year of attribution, many marketers (and their bosses) still aren't clear on exactly what attribution is. The concept is simple: You attribute credit and value where they are due.
And in today's analytics-driven, multichannel world, we all want to know not only whether what we're doing is working but also where, when, with whom, and how well.
But drill down a level, and most marketers are unclear which measurement approaches are right for their business:

• Do I need high-level insights around budget planning, or tactical insights to optimize in a channel?
• What can I get out of my existing tools, like site-side analytics?
• When do I need something specific?
• What's the difference between all the solutions that claim to offer attribution, and which one makes sense for me?

To answer those questions, marketers need a clear understanding of their options. That starts with defining two of the most common approaches to marketing measurement: marketing mix modeling (MMM)—used interchangeably with media mix modeling—and attribution.
Both MMM and attribution are sophisticated models for measuring cross-channel marketing activities, but they work in different ways, for different reasons.

Marketing Mix Modeling and Attribution Defined
Search for the "technical" definitions of MMM and attribution, and you won't get very far in deducing their differences. Gartner defines marketing mix modeling as "analytical solutions that help marketers to understand and simulate the effect of advertising, and to optimize tactics and the delivery medium."
Gartner's glossary doesn't offer a definition for attribution, but its friends at Forrester define it like this: "The practice of using advanced statistical approaches to allocate proportional credit to marketing communications and media activity across all channels, which ultimately leads to the desired customer action."