Tag: CBC

Constrained Choices in Choice-based Conjoint Analysis

Posted on by Caroline Lewis

An essential concept in consumer decision-making is that choices are made under constraints. Chiefly among these are having enough time and enough money, which are particularly pressing in today’s post-pandemic, inflationary climate.

As additional examples, limitations like dietary restrictions on ingredients such as salt, sugar, or gluten also constrain purchasing decisions.

However, a notable oversight of traditional Choice Based Conjoint Analysis (CBCA) as typically applied is its failure to account for any constraints whatsoever.

In particular, CBCA does not incorporate the buyer’s money budget into its price sensitivity estimations and predictions.

A new feature of the in4mation insights’ (i4i) choice modeling toolkit is Budget-Constrained CBCA (BC-CBCA) which operates on two straightforward assumptions:

    • First, any product priced beyond an individual’s budget when presented in a conjoint survey, is disregarded, rendering its value null — no amount of brand prestige or appealing features can influence its selection. We do acknowledge that, in special situations, people will exceed their budget, yet not by that much, creating a new, slightly larger budget constraint.
    • Second, for items within their budget, consumers exhibit relative price insensitivity, reasoning that, “If it’s within my budget, I can afford it.” BC-CBCA , as we apply this innovation, starkly contrasts with traditional CBCA by directly incorporating budget constraints into the decision-making process.

Consequently, price sensitivity for items under the budget limit is less pronounced. This leads to substantial differences in predicted overall choices between BC-CBCA and standard CBCA.

Importantly, in i4i’s BC-CBCA approach, the budget threshold does not have to be asked in the survey. Rather, it is estimated probabilistically based on participants’ choices within the context of the CBCA task. We note that the budget limit can be asked in the survey, but in that case it is a first approximation of what BC-CBCA will eventually calculate and use in estimation of the magnitude of all choice drivers.

An Example

Several years ago, we conducted a study looking at the choice of digital cameras. Roughly 450 prospective buyers replied to eight choice situations. Each situation had four brands or none to choose from. About ten attributes were investigated, including seven brands and prices that ranged from a low of $199 to a high of $459.

We counted the number of people who BC-CBCA estimated to be budget constrained; that is, they would not purchase a camera that cost more than the maximum price of $459. We found that about one-third have a budget greater than the maximum price shown in the survey (we call them unconstrained) and about two-thirds are budget constrained, meaning their budget limit is less than $459.

If we look only at those people who are constrained, we can estimate their maximum willingness to pay, in other words, their budget limit. Looking at this chart, you can see the percentage of people whose budget limit is at each of the bars, $10 at a time. The red line shows the cumulative percentage of people below the maximum price displayed, all of whom are budget constrained, but at different limits.

For example, the second blue bar from the left crosses the Y-axis at 20% indicating that percent of people have a budget limit that is $270 or smaller. If you mentally group the bars, you might say that there are three-four segments of people with budgets at different limits.

As previously mentioned, the constrained budget model yields a different price sensitivity than the standard approach does. To demonstrate this, we first created a “base case” of cameras with their features and prices. We chose camera brand “N” as our test of the price sensitivity. Displayed in this chart is the predicted choice share on the vertical Y-axis. The horizontal X-axis goes from $0 to $1000, although $199 was the lowest price evaluated across all brands and $459 was the highest price tested price. At the lowest price of $199, the two approaches – budget constrained and standard MNL –both predict a choice share of just over 50%. However, at the highest price evaluated, the standard approach predicts a choice share of 30% and the budget model predicts a little over 10%. Which seems more realistic and believable to you?

The budget constrained model has a much steeper price-choice curve. Why is that? As the price increases, the budget limit of individual people is being reached.

When the price exceeds their budget; the product becomes unaffordable and they “drop out” of buying that camera.

To show that the budget model will deliver more realistic results, we increased the price of camera N to $1000, as shown below. In this case, you will note that the standard MNL analytic model predicts that 10% of buyers will still chose Brand N – even at a price that is more than twice the maximum tested!

On the other hand, the budget constrained model delivers a more realistic result: no one will purchase at $1000, and in fact, the budget approach reaches 0% choosing “N” at around $800.

What is happening in the budget model versus standard multinominal logit (MNL) models? The standard only has one way to measure the effect of price (price sensitivity) while the budget constrained model has two ways (price sensitivity and a budget constraint). Since the standard model is “missing” the budget information, it increases the price sensitivity to make up for the fact that the budget limit is unknown.

Summary

Employing constraints in advanced CBCA offers more realistic predictions of buyer behavior across various categories, including hotel and travel selections, durable goods, electronics, premium products, and even groceries purchased at supermarkets. BC-CBCA distinguishes between individuals with financial constraints and those without, identifying segments of individuals with similar budgetary limitations.

This enables tailored product designs and offerings for different buyer groups with different constraints. Additionally, in BC-CBCA, we have observed that once the budget is accounted for, the role of price diminishes, and brand and product features play larger roles in influencing purchases.

Next Steps

BC-CBCA works. It produces deeper insights than the traditional approach.

We can show you.

We will even run BC-CBCA with your data from a standard CBCA project that you completed in the past.

That’s how sure we are of the power of BC-CBCA.

If you wish to fine tune your understanding of how consumers make choices regarding your products and services, by leveraging Budget Constrained – Choice Based Conjoint Analysis, contact us to discuss your challenges at info@in4ins.com.

Four Next Generation CBCA Tools to Understand How People Make Choices

Posted on by Caroline Lewis

Marketing aims to influence the decision-making moment when a buyer selects your brand or item. This choice translates to adoption, increased revenue, loyalty, and growth. For decades, researchers have been looking for an unquestionable source of data-supported insights to determine what influences consumers’ choices and guides decisions. With this information, companies can set priorities for customer experience, product development, optimal pricing, and messaging, ensuring that choice equals sales and ultimately enabling businesses to measure ROI of marketing initiatives before engaging in them.

Since its inception, Choice-based Conjoint Analysis (CBCA) has proven invaluable for brands aiming to grasp consumer behavior. Initial developments in CBCA evolved into useful survey techniques focused on unraveling decision hierarchies and understanding how tradeoffs influence decision-making. Undoubtedly, the methods developed years ago were revolutionary for their time, but even the best marketing research methods have their shortcomings. What was previously thought of as the “gold standard for choice modeling,” has reached its limits without further refinements based on in-depth understanding of human behavior.

As a pioneer in the introduction, development, and commercialization of CBCA and related tools like MaxDiff and Menu-based CBCA, I can tell you that it is finally time for our industry to step up, to stop using outdated and simplistic models and methods, and to embrace superior solutions.

Advancements in the science of decision-making have spurred innovations that challenge conventional wisdom by incorporating more robust behavioral assumptions. These developments, primarily driven by academic research, remain largely unknown to most practicing researchers.

As longstanding pioneers in applying choice methodologies to marketing issues, in4mation insights (i4i) continues to leverage state-of-the-art techniques to tackle our clients’ evolving business challenges. Stemming from our extensive investigations in marketing science and behavioral economics, these innovations enhance our ability to forecast choice behavior and to drive superior business outcomes.

These new advancements in choice modeling, as elaborated below, greatly improve our comprehension of the factors influencing consumer choice. The insights derived from these innovations empower companies to better uncover optimal product attributes and pricing models that resonate with consumers, all while understanding the intricacies of decision-making within the confines of their everyday lives and budgets.

These are not minor adjustments – we are highlighting these advancements to fundamentally overhaul CBCA’s alignment with data, altering the direction and intensity of choice effects, yielding more precise predictions of consumer behavior and business results.

Our new advances in CBCA tools are:

1. Constrained Choices

An essential concept in decision making is that all choices are made under constraints. Primarily among these are having enough time and enough money, which are particularly pressing in today’s post-pandemic, inflationary climate.

An individual buyer’s budget offers a threshold beyond which they will not purchase an item, no matter its attractiveness. With so many news articles describing how consumers and businesses are tightening their belts and watching what they buy, understanding the role of a budget in choice is even more critical than it has been in the past.

However, while CBCA does not incorporate the buyer’s budget into its price sensitivity estimations and choice predictions, a new Budget-Constrained CBCA (BC-CBCA) does just that.

By employing budget constraints in CBCA, our i4i approach offers more realistic predictions of buyer behavior across product categories, from expensive durables to groceries purchased at supermarkets. BC-CBCA identifies segments with similar budgetary limits, thus enabling product designs and offerings tailored to different groups. Importantly, the underlying math of BC-CBCA guarantees a fit to the data that is as good as or even better than standard CBCA.

2. Do people pay attention to everything?

A foundational assumption of standard CBCA is that everyone processes all the information available to them and they make compensatory trade-offs. But what if they do not, and instead, they use simplifying rules to pay attention to just a subset of the information? Attribute Non-Attendance (ANA) uncovers who does and who does not pay attention to all the information. The result is that ANA enhances traditional CBCA by offering more accurate predictions, since it enables us to uncover the impact of the true salient attributes affecting choice. Our recent work has revealed that sometimes as little as 10% of consumers consider all attributes in their decision-making, strongly challenging the bedrock assumption of standard CBCA.

3. Asymmetric and Symmetric Choices

The standard statistical tool of CBCA is Multinomial Logit (MNL) which governs the math behind choice modeling. A less well-known aspect of MNL is its symmetric prediction of choice behavior. At a 50% likelihood of purchase, equal increases or decreases in product attractiveness (utility) will produce equal gains and losses in choice shares. The symmetric property can lead to unrealistic predictions, especially when the final predicted choice shares among alternatives varies widely — a scenario all too common in virtually all choice studies.

A new enhancement to standard MNL abandons the symmetry assumption in favor of asymmetry. At i4i, we have found that employing asymmetry in choice fits choice data better than symmetric MNL, more accurately reflecting real-world decision-making patterns, and yields vastly different choice share predictions.

4. Regret minimization (RM) versus Utility maximization (UM)

While conventional CBCA approaches assume that buyers aim to maximize the utility of their purchases, some opt for products that help them avoid losses. In contrast to Utility Maximization, Regret Minimization closely aligns with the behavioral economics principle that “losses loom larger than gains.” If we acknowledge that not all people are utility maximizers, it’s crucial to have choice models that can accommodate different decision-making strategies. Our experience at i4i has proven that a hybrid method, recognizing that some individuals prioritize maximizing utility while others focus on minimizing losses, produces superior results, rather than a monolithic approach where all individuals exclusively use UM to the detriment of RM or vice versa.

=  =  = =  =  =  =  =

We will be expanding on the details behind these four new developments in choice modeling in the coming weeks.

We are excited about the potential that these new cutting-edge enhancements to CBCA tools offer marketers, especially during these challenging times.

Whether these innovations address the gaps you have encountered with traditional CBCA or if you’re simply intrigued by their potential application in your business, please reach out to us at info@in4ins.com.

Let’s explore how we can enhance your choice architecture to drive sales growth.

The standard method of determining price sensitivity is flawed! But there is a better way.

Posted on by Kevin Youts

It is always tough when we discover that the gold standard for decision support in any business challenge needs an update, if not total rethinking. Such is the case with the broadly accepted “best practice” approach to determining price elasticity and the optimization of the products, features, and prices of almost all products and services.

For decades, companies have depended on choice analysis to identify the features and attributes, the tradeoffs that consumers will make, and the price parameters they will accept when considering a purchase. Choice-based conjoint (CBC) analysis ascended from its inception in the early 1980s to wide acceptance as the preferred methodology for pricing guidance, eventually with adoption of software that in theory makes the process more automated.

As with most more complex analyses that depend on higher level math, tools like CBC are best applied by the experts who understand not only how the algorithms work, but also the basic behavioral and economic science that is foundational to what the analysis is uncovering.

As one of the innovators who were part of the introduction of CBC, we are huge proponents of the elegance and utility of CBC to help marketers understand the drivers of choice. We know that psychologically, consumers assess product purchases based on complex, personal, stated and unstated decision rules, which CBC is perfectly positioned to identify and predict their impact on price.

We have been at this for decades. At some point, we have to take a hard look at the limits of CBC as it is typically implemented. And for the sake of the industry, we are forced to say that we can do better.

So what is the problem?  And how can we fix it? 

The classic approach to CBC looks at preferences, but ideally you want it to also reflect the constraints that may define the preferences.

Time can be a constraint that impacts price. If I need a product or service within a specific time frame, I might be willing to pay more to obtain it. Or if time is not as pressing, a lower price may be the key attribute that will influence a purchase. We see this principle every day in the choice of shipping options in online commerce.

But beyond preferences, the constraint of a money budget imposes a consideration that may be an even more powerful motivator/demotivator to making a purchase choice. I may want a phone with extended battery life, or a car with luxury accessories, or I may want the luxurious and expensive skin moisturizer. But my money budget constraints, relative to all my other payment obligations, may make those unacceptable choices. Traditional CBC is not structured to accommodate the money budget as an attribute, and its omission distorts the size of those factors that are impacting buyer choice behavior.

Using a money budget in a choice model yields estimates of price sensitivity that are dramatically lower than the price sensitivity estimates found in choice analyses that do not employ a budget. This guarantees drastically different implications for price setting.

How does it work?

Budget Constrained CBC assumes that each person has a fixed budget for purchasing in a product category.

  • If a purchase option costs less than their budget, it will be considered and the product may or may not be bought, depending upon the benefits it provides.
  • However, if an option costs more than their budget, it will never be bought.

Let’s look at an example. These are the price sensitivity coefficients estimated in a study of purchasing a consumer durable. We studied choice behavior using CBCA with about 500 people who were “in the market” for a new model of this product.

We estimated a price sensitivity value for each person using the standard approach and also the budget constrained method. We can look at the percentiles of the distribution of price sensitivity across all people. This table shows the results.

The table shows the results of the percentiles of the distribution of price sensitivity across all people.

The price sensitivity for the budget approach is “flatter” than for the standard model and is roughly half the size (-.491 versus -1.080).

The table shows that:

  • All price sensitivities are negative, as they should be under economic theory.
  • Mean price sensitivity under the standard approach is more than twice as large as the sensitivity under the budget constraint.
  • The variability of the price sensitivity under the standard approach is about 50% more variable than under the budget constraint.

By ignoring the buyer’s budget, traditionally applied CBC will yield results that tell you that people will spend more than they actually will do and it tells you that people are much more diverse and variable in their estimated price sensitivity.

Building the Better CBC Model

The defect inherent in the gold standard of is corrected by estimating the buyer’s budget and including it explicitly in CBC.

Budget Constrained CBC overhauls this fundamental flaw and delivers more accurate estimate of willingness-to-pay, better fits to raw data, and deeper insights into buyer behavior.

Seems logical to you? We would love to prove it to you that it works. If you have an old CBC study for which you have the data and would like to see the results delivered by the constrained budget approach, contact steve@in4ins.com to discuss.