A magic model to aid marketing managers
R. K. Reddy
Tara, the marketing manager of the FMCG giant, Cleanactive, is staring at the graph on the screen in front of her. She is disappointed with the market performance of the brand portfolio under her during the previous financial year. The brands experienced a smooth decline in sales volume despite increased advertising and promotional efforts.
Then comes a `mathemagician' who claims to revive the brands and restore the lost sales volume while bringing down the rupee spend on various advertising and promotional activities, and all he asks for is the sales and marketing-efforts data during the last couple of years.
From his bag of tricks he takes out a strange-looking crystal ball which he calls the Marketing Mix Model. It looks strange as it has two surfaces - one shows the past while the other shows the roadmap for the future. Observing the confusion on her face, he explains that the roadmap for the future is the reflection of the past and is the function of all the activities in the past. He asks the marketing manager to help him look into the former surface and he will let her see the roadmap into the latter that leads to her brands' revival.
Marketing Mix Modelling (MMM) is an analytical approach that uses past data (syndicated point-of-sale data and companies' internal data) to quantify the sales impact of various marketing activities. Mathematically, this is done by establishing a simultaneous relation of various marketing activities with sales in the form of a linear or a non-linear equation, through the statistical technique of regression.
MMM defines the effectiveness of each of the marketing elements in terms of its contribution to sales-volume, effectiveness (volume generated by each unit of effort), efficiency (volume generated by each rupee spend) and ROI (rupee generated by each rupee spend). These learnings are then adopted to adjust marketing tactics and strategies, optimise the marketing plan and also to forecast sales while simulating various scenarios.
All product industries, especially FMCG, are highly driven by marketing efforts that include advertising on various media channels and promotions to retailers or consumers. Companies are spending up to 40 per cent of the top-line sales on such marketing activities. Mathematical data modelling can help increase efficiency of this spend by up to 30 per cent. With the increasing number of channels to advertise their brands, marketing managers like Tara are facing huge challenges identifying the right mix of channels for advertisement.
The issue becomes more challenging in the light of each channel getting cluttered with more and more brands being introduced into the market and each trying to speak louder. Each player in the market is spending more and more while not increasing their share of volume or even the absolute volume.
A potent device
MMM is a powerful tool that helps managers identify the right mix of channels for advertising and hence make better business decisions in terms of allocating marketing spend and media planning - not just allocation to various channels of marketing but also the allocation to each channel across time periods.
For instance, a major brand in the Philippines was to identify a couple of effective media channels, other than conventional ones, for its promotion. Marketing mix modelling helped identify those, and they turned out to be e-mail campaigns and in-store promotions. These could deliver higher ROI as compared to conventional media.
MMM equips managers with the knowledge and understanding of the due-to and the what-if scenarios, like what if the entire TV spend from one region is shifted to another, what if part of the print spend is shifted in launching a new TV ad copy? Managers can better evaluate the trends and forecast the volume through their marketing activities. They can anticipate the consumer response to marketing activity, and can identify the upside potential and downside risk of changing marketing spends. Additionally, MMM helps them to evaluate the performance of various kinds of in-store or direct-to-consumer promotions. It tells us the success rates of various new product introductions or other initiatives and the reasons for it.
A recent MMM study showed that new initiatives for a leading hair-care brand in Australia were becoming less effective in boosting the sales volume, and a deeper diagnosis revealed that these initiatives were drifting away from the core equity of the brand and also that they were lacking holistic media support. Managers realised this and planned future initiatives accordingly to make them more effective.
The impact of pricing (both own and competitors') and distribution (both width and depth) can also be gauged through MMM, which helps managers identify the optimal price vis-à-vis competition and the right markets to be present in with optimal spread and the optimal number of items. Another recent study in Mexico identified the optimal price for a large SKU in a club store vis-à-vis small SKUs in other stores in order to get the most out of buyers and still retaining the loyal customers. All this taken together gives managers a huge competitive advantage.
The insights that this tool can provide can go far beyond the limit that marketing managers can imagine. For example, in TV advertising activity, we can know how each ad copy has performed in the market in terms of its impact on sales volume. We can gain insights into the direct and the halo effect of TV activity.
For instance, various liquor brands advertise their mineral water or music CDs by the same name and have a positive impact on their liquor sales. MMM lets one measure this impact and optimise advertising spends across various products or sub-brands under the same brand. We can know the effectiveness of a 15-second ad vis-à-vis a 30-second ad. We can find out how an ad has performed during a prime-time slot and during an off-prime-time slot. Hence depending on the differential cost, one can identify the most favourable way to allocate TV advertising budget.
MMM also tells us the effectiveness in terms of volume response at various levels of gross rating points (GRPs) within a time frame, be it a week or a month. We can identify the minimum level of GRPs (threshold limit) in a week that need to be aired in order to make an impact; we can spot the level at which the activity gives maximum ROI; the level of GRPs at which the impact on volume maximises (saturation limit) and that the further activity does not have any payback. The role of new product-based TV activity and the equity-based TV activity in growing the brand can also be determined.
Looking deep into the element of distribution, we can discover how the volume will move by changing distribution efforts or, in other words, by each percentage shift in the width or the depth of distribution. This can be identified specifically for each channel and even for each kind of outlet for off-take sales.
In view of these insights, the distribution efforts can be prioritised for each channel or store-type to get the maximum out of the same. A recent study of a laundry brand showed that the incremental volume through 1 per cent more presence in a neighbourhood kirana store is 180 per cent greater than that through 1 per cent more presence in a supermarket. Now based upon the cost of such efforts, managers identified the right channel to invest in more for distribution.
The very break-up of sales volume into base (volume that would be generated in absence of any marketing activity) and incremental (volume generated by marketing activities in the short run) across time gain gives wonderful insights. The base grows or declines across time while the activities generating the incremental volume in the short run also affect the base volume in the long run.
A leading hair-care brand was losing its base, and an MMM study identified the reasons as increasing price (hence reducing value perception of the brand) and the increasing competition. The immediate need was to air equity-based ad copies on TV and other media that could help improve brand equity. The other immediate action was to reduce price-based promotional schemes that were also diluting the equity. This helped revive the brand, and saved the brand from possible extinction in the long run. Clearly, the knowledge of such impact of each of the incremental marketing activities on the base volume assists developing long-term strategies to increase base and hence the net worth of a brand.
Moving one step further, studying various brands together can show the way to optimise the portfolio of brands within a product category. This happens when we know the extent to which an activity in support of one brand impacts/cannibalises another brand. The net payback on the overall portfolio is something that needs to be considered from each of the activities in support of various brands, and accordingly plan the spends.
All that the marketing managers need to do to gain this competitive advantage is to better manage their data and seek help from those mathemagicians.
Most believe that the kind of data available in the developing markets like India is not enough for carrying out such analysis because of the lack of organised retail wherein most of the sales still coming from the unorganised mom-and-pop stores, the data collection, compilation and even the integrity of data is doubted.
As against developed economies like the US, where data is automatically generated through scanners at retail outlets, in developing markets like India it is gathered through retail audits which is conducted once a month. This restricts the collection of data to a monthly level while it can go down from weekly to daily to consumer level and up to transaction level in developed and organised retail markets. The MMM can be developed and its insights can provide a never-before competitive edge for the brands in the Indian market even with the current level of data available.
Typically, the marketing budgets for a brand are identified in proportion to its overall worth. These spends/activities should ideally enhance its value and subsequently facilitate a higher budget for marketing managers. This becomes a virtuous circle for the business and the brand experiences a steady growth. A very effective entry point for this virtuous circle is an MMM that shows the right way to spend the budgets to make the maximum impact on volume and hence the worth of a brand to make it grow.
Notes: A club store is a large retail outlet that sells only large-size item (or large bundles of small sizes) and only to the registered members of the store. One such store in India is Metro, in Bangalore.
Halo effect is the impact on volume of a sub-brand through advertising another sub-brand under the same umbrella brand.
R. K. Reddy is Director - EMEA and India, Fractal Analytics and Amit Gupta is Business Consultant, Fractal Analytics)