Managing product categories for optimal performance in foodservice presents three key challenges that category partners need to solve: how to manage data reporting and analysis, conduct effective selling logistics, and close the sale. This post examines these three problems and identifies practicable solutions for manufacturers in collaboration with their distribution partners.

Data Reporting, Management and Analysis

Manufacturers often do not have regular, dependable access to sales data. Transaction information typically resides downstream, so the manufacturer must negotiate with its distribution partners to establish a mechanism for information sharing. Assuming such agreement is reached, the process may give rise to a variety of data problems. Data integrity issues are prominent among these. It is unlikely that the manufacturer will receive specially prepared sales reports – information more probably will come in the form of raw data untreated for accuracy, correctness or clarity. Readers of these reports will find it hard to obtain insights in them from which to take action on a timely basis.

What needs to happen to remedy this problem is a deeper level of collaboration between the manufacturer and distributor where each side is able to contribute the insights it possesses – product attribute knowledge from the manufacturer, customer purchase habits information from the distributor – and share this information via a common data platform. Bringing this information together in a robust data environment can help manufacturers and their partners obtain intelligence from which to make decisions about the right products to bring to targeted customers.

Sales & Marketing Logistics

Once category partners deal with the data management problem and successfully come up with actionable insights, they then need to figure out how to get those insights through the channel. “How do we get the right products onto the store shelves?” is how this exercise typically goes in the retail industry. But in foodservice a different question must be asked: “How do we get the sales representatives in the field to know what products we want to offer to specific customers, and to call up that knowledge in real time when the opportunity presents itself?” That is a different challenge than the one commonly addressed by simple SKU rationalization.

Bear in mind that the typical sales representative or marketing associate (MA) in foodservice has a full plate of selling and administrative duties he or she must perform every day, and not much capacity left over for assimilating and processing new information. Bear in mind as well that this typical MA may need to have on tap individual SKUs from over 200 product categories to supply to the regional customer base as demanded. That is far more information at the product-customer level than the MA can be expected to keep in mind without the benefit of effective selling tools. However, the MA cannot be expected to readily go up a new learning curve each time a manufacturer comes along with a new sales tool to apply to one of those 200 categories. MAs must be spoon-fed with the simplest, least time-consuming methods to get the right recommendations through the pipeline to the right customers. That means relying on what is already familiar to them, rather than overburdening them with new methods and processes.

Closing the Sale

That brings us to the last of the three challenges. Having managed to get the right products to the right customers, there remains the task of convincing the customer to actually make the purchase. Two things can help improve the odds of getting to yes. The first is knowing what combination of price and promotional discounts to offer to encourage the customer to switch from its current provider. The second is being able to back up the offer with relevant, impactful product collateral to drive home the key advantages of the products you are trying to sell.

Now, remembering that the sales representatives lack the capacity to juggle lots of different sales tools, how is it possible to actually mobilize all this information – price and promotional terms and supporting collateral – link it, and bring it to bear at the point of sale?

The Benefits of Working Backwards

The key is to keep it simple, and the best way to do that is to work backwards from the point of sale. It pays to ask how the salesperson can make this sale, armed with the right information, with as much ease and as little extra expended effort as possible. In the course of their work salespeople will tend to make use of certain selling tools on a regular basis. When a salesperson already knows how to use a tool and understands why it delivers performance benefits, a big part of the challenge is solved by leveraging off that tool to deliver category management initiatives.

Working backwards is not intuitive to everyone. Too often, when thinking about the implementation of a new performance system, decision makers create pages and pages of process work flows and front-end requirements and organizational change management specs, without asking themselves how it is going to work, realistically, in practice. A better approach is to envision how, at the point of sale, the salesperson can (a) know the right products to sell to certain customers, (b) be armed with pricing and promotional offers to increase the odds of inducing the customer to purchase from him or her, and (c) have appealing and persuasive collateral at our fingertips to close the deal. What can category management partners do to most effectively accomplish this given the constraints on the salesperson’s time and information capacity? Working backwards can offer a higher likelihood of both partners getting an impactful, measurable return from category management collaboration.

Looking at the human mind this way, as a machine constantly evaluating possible outcomes based on prior knowledge and assigning probability weights to those outcomes, gave rise to the notion of the “Bayesian brain,” a term popularized in 1983 by Geoffrey Hinton of the University of Toronto and Terry Sejnowski of Johns Hopkins University.  This notion has subsequently received a good amount of validation by neuroscientists as they continue to make advances in understanding how the brain really works.  Neuroscientists Alexandre Pouget and David Knill of the University of Rochester in 2004 referred to a “growing body of evidence that human perceptual computations are ‘Bayes optimal’ (“The Bayesian brain: the role of uncertainty in neural coding and computation,” Trends in Neurosciences, vol 27 issue 12, December 2004, pp 712-719).  That’s a fancy way of saying that we make estimations based on likelihood – for example we routinely make estimations about things like the distance from us of an object, or the speed at which it is traveling, based on our prior knowledge of the shape, clarity and movement patterns of such objects and the likelihood that the present reality fits into that a priori knowledge.

So far, so good.  But there is an Achilles heel to our hierarchical mental gymnastics.  Briefly, we may be great at the kind of proposition-within-proposition reasoning that our sales rep exhibited in getting to the essence of the competitive threat posed by the wholesaler’s move to town.  But we humans are generally pretty lame when it comes to computation.  Our intuitive reasoning skills fail at the task of instantaneously calculating that 34 x 57 X 71 = 137,598.  One way that we get around this failing is through heuristics – basically, shortcuts that we use in conditions of uncertainty to help us get from information to evaluation and decision.  Take the example above of evaluating the distance a particular object might be from us.  Now, there is a physics formula we could apply to measuring distance, height, momentum (if moving) and so forth to give us the precise answer as to how far away that bicyclist in the yellow jersey is from us.  But our brains lack the ability to do spontaneous physics equations.  Even if we precisely knew one or more of the variables it would be hard to do an on-the-spot computation.  So we need something else – a proxy, a heuristic.  That something might be clarity.  Can we see the bicyclist clearly?  Can we make out the details of his black helmet with red stripes, and the ‘Elf Aquitaine’ logo on the yellow jersey?  That can give us enough information to call upon our “cyclist in a yellow jersey” neuronal connections and infer a likelihood that he is, say, 50 yards away.

The problem with heuristics is that they are subject to error: not occasional lapses in judgment but systematic, predictable biases.  For example if we use clarity as a heuristic we may overestimate the distance of that cyclist from us if there is poor visibility.  Understanding the role of heuristic errors in human judgment and decision making was one of the main contributions of Amos Tversky and Daniel Kahneman to our understanding of behavioral factors in human decision-making (“Judgment Under Uncertainty: Heuristics and Biases,” Science New Series vol 185 no. 4157 Sep 1974 pp 1124-1131).  Tversky and Kahneman documented specific heuristic errors such as representativeness (drawing broad or sweeping conclusions from a limited data set), availability (assigning the likelihood of an event based on the easiest example that comes to mind, whether or not appropriate, and anchoring (relying heavily on one piece of information when making a decision even if it is irrelevant).

Since heuristic errors are part and parcel of human judgment and decision-making under uncertainty, we have to take this reality into account when we attempt to integrate quantitative modeling methods and qualitative human judgment.  What are the best mathematical tools and frameworks to integrate these two domains?  One area in which we at Sentrana are spending considerable time is that of Bayesian hierarchical modeling. The Bayesian approach is particularly useful in marketing situations such as modeling differences in the needs and wants of customers using both generalized and conditional assumptions involving multiple variables. Bayesian frameworks provide a natural way to pool disparate sources of information. A Bayesian model requires the formulation of prior distributions and the estimation of a likelihood function, which can add complexity to the model-building process.  However we expect future insights and innovations in this area, alongside the development of more robust computation capabilities to bring more firepower to bear on this difficult but potentially valuable quantitative approach.

But let’s take a different look at this apparent tight coupling of mathematics and dire outcomes. Our recent correspondence with an author who has been widely published on the subject of Wall Street’s use of mathematical models recently offered to us an interesting opinion. His point was that the problem with the models was not so much their complexity, but rather that they were models in the first place. His argument was that you can’t ever perfectly hedge model risk.  Now, I agree with that observation: a model by definition selects some aspects of reality to represent and omits others, and the choice of what to include and what to omit is subject to human error, therefore fallible and not perfectly hedgable.  But I take issue with the idea that the fault lies in the existence of the models themselves.  Models can be misused – I think that much is clear. But the notion that models are all doomed to failure obscures a deeper truth about the goals of predictive modeling; namely that you can seek either to reduce the world or truly explain it. By trying to elegantly reduce the world to as few predictor variables as possible, you are more likely to be sowing the seeds of future failure, because complexity and actual drivers of outcomes are taken out of the equations to make them more solvable (or perhaps sellable, as in the case of the Gaussian copula function that was behind Wall Street’s demise, as we discussed in a previous posting “You Can’t Punt Away the Dimensionality Curse”). Predictive modelers don’t have to go down that road, however: they can also set out with the goal not of reducing an entire system to a single neat, tractable equation, but to quantify and explain all of the relationships that dictate outcomes to the absolute fullest extent possible. Tractability and computability are things to address later in the process, through technological means, but they should not dictate the fundamental mathematical approach at the outset.

As I see it, the problem with the financial market meltdown is not that David Li published an article in the Journal of Fixed Income Securities on the Gaussian copula function, or even that in his article Li, then an analyst with JPMorganChase, identified the price of credit default swap (CDS) contracts as a seemingly elegant proxy for the mortgage market – a proxy that greatly reduced the immense complexity of modeling values and risks in this market but, as it turned out, lost a great deal of critically important information along the way.  No – the real problem was with the incremental decisions practitioners made to adopt this model wholesale, to leverage it up to 50 or more times the worth of the underlying assets, and ultimately to heedlessly employ it as a path to untold riches.  In other words it was the people who used the model, not the model itself.  It was the rating agencies who, in conferring the AAA ratings without which the securities would have never been as widely distributed as they were, assumed that housing prices would never go down.  It was the investment bankers who successfully shouted down the warnings of their internal credit risk departments so that they could sell ever higher volumes of CDOs, with ever-higher levels of leverage, in order to maximize their year-end bonuses.

You can’t fully hedge model risk – that is true.  But you can mitigate model risk through the application of robust decision-making processes.  A model did not take down Wall Street. Models do not “screw up” – they do exactly what they are supposed to do once they have their inputs. The screw-ups occur solely in our application of models to inappropriate situations or to situations which we do not fully understand. The predictions may not reflect reality outcomes as precisely as we wish, but that possibility of error needs to be accounted for by the ultimate decision makers. The output of a model should be an input in any decision process, not the entire decision process. For that reason, the emerging generation of predictive technology solutions being employed by all varieties of business seeks to marry model holism (by including ALL of the relevant variables, rather than the most computationally feasible), computational firepower, and above all, ranges of probability-based recommendations, rather than a single output. It may sound heretical at the moment given the present economic calamity, but as the world gets ever more complex, models will become more valuable to decision makers, not less. Informed, prudent decision-making in regard to those models will not be a luxury, but an absolute necessity.