Tag: configuration
Connect With Us
Take Rates – What are the most popular product choices?
I want to apply the discussion of entropy to the features of a configurable product. But first we have to introduce the important concept of a “take rate”. In different industries this is called an “attach rate”, or a “penetration rate”. The idea is very simple: the take rate of an option is the fraction of units sold that include that option.
The take rate of option x is the number of units sold with option x, divided by the total number of units sold. So if 70% of our cars are sold with cloth seats and 30% with leather seats, then cloth has a take rate of 0.7 and leather has a take rate of 0.3.
In the case of a feature with two options, like cloth and leather, this looks just like a coin toss with two options, tails and heads. Recall that coins may not be fair. If I send you a message about a customer’s choice of seat, the entropy of that message is the same as for the outcome of one toss of a suitably biased (.3 to .7) coin. So take rates can be interpreted as probabilities.
Some features have more than two options. For example a backhoe feature called Feet has four different options: none, Flip, Flip Guard, and Street Guard. Each of these options has a take rate, and as long as we include the “none” option, these take rates have to add up to 1.0. So perhaps 30% of customers do not order Feet, 40% order Flip, 20% order Flip Guard, and 10% order Street Guard. The take rates are 0.4, 0.3, 0.2, and 0.1, respectively, which add up to 1.0.
With four options we lose the connection to coin tosses. We could use a loaded die to talk about features with six options, but an all purpose metaphor is the roulette wheel. Think of a spinning roulette wheel, or a stationary wheel with a spinning arrow as in many children’s games.
The wheel represents a feature, and there is a pie-slice for each option. The size of the pie-slice is proportional to the take rate. An example is shown above for the Feet feature of our backhoe. We can simulate a customer’s choice by spinning this wheel (or spinning an arrow). With this metaphor we can have any number of options, with any take rates. The “none” choice must be included to get a full pie (or there may not be a “none” choice).
To summarize, a product is a collection of features. Each feature has some mutually exclusive options, each of which has a take rate. These take rates add to one.
The Entropy of a Coin Toss.
A product is a collection of features, and each feature has mutually exclusive options. If a feature has only two options, then the choice is like a coin toss. The information contained in that choice is measured by entropy.
Entropy is a concept from classical thermodynamics that deals with the amount of disorder in a physical system (see http://en.wikipedia.org/wiki/Entropy). It was extended to information theory by Claude Shannon (see http://en.wikipedia.org/wiki/Entropy_(information_theory)). Shannon used entropy as a measure of the amount of information in a message. The simplest example is a coin toss. If we toss a fair coin, there is a 50% chance of getting tails, and a 50% chance of getting heads. Shannon defined the outcome of this experiment as having an entropy, or information content, of one bit. If I send a message (say 0 or 1) to tell you the result (tail or head), that message contains one bit of information.
Things start to get interesting when the coin is not fair. Consider a two-headed coin. The tossing experiment always results in heads, and the message will always be 1. According to Shannon, the information content of this message is zero.
If the coin is weighted so that the probability of tails is 25% and the probability of heads is 75%, then Shannon assigns an entropy of 0.811278. There is some information in knowing the outcome of the coin toss, but not as much as for a fair coin, because we already know that it will probably be heads. The graph below shows the entropy as a function of the probability of getting heads. When this probability is zero or one, the entropy is zero. The entropy reaches its maximum of one when the coin is fair (50%).
Where did the 0.811278 come from? How is the entropy actually computed?
We can’t answer this without introducing logarithms to the base two. In English, two to the third power is eight, so three is the logarithm of eight to the base two. We can write “blog” to mean log to the base 2, or binary log. If p denotes the probability of heads, then entropy is computed by the formula:
Entropy = -p*blog(p) – (1-p)*blog(1-p).
Logarithms to the base 2 arise naturally because one coin toss (2 outcomes) has entropy one, two coin tosses (4 outcomes) has entropy two, three coin tosses (8 outcomes) has entropy three, and so forth.
Comments Off
The quality connection
Recently I wrote about quality rankings for automotive manufacturers and the perception of these rankings in the market. While the marketing teams at these companies must shoulder the burden to convince consumers about their products’ quality, there is a very real connection between product quality and configuration management.
In many industries where products have grown over time with constant additions of new features and flexibility to allow customers to build to order, the level of complexity is staggering. Often the number of configurations sold on an annual basis is surprisingly close to the total units sold for that same period. This “snowflake” situation is one of the worst possible scenarios in product complexity as each unit has its own signature. Obviously, the production of these products also requires flexibility in manufacturing. This may result in reduced use of automation, and often it leads to units being reconfigured where components installed during one step are either removed or modified in a later step due to a unique situation.
These one-off manufacturing processes open the door for product quality issues due to fewer controls during production. Put simply, if I can reduce the number of different things that must be done during production I should be able to do those things better.
So product management teams have direct input on product quality via product complexity. Managing the product option mix to reduce the overall number of configurations can promote the increased quality that all manufacturers are looking for.
Comments Off
Help the sales team help the customer
This morning I was talking to the VP of business process improvement for a company that sells industrial machinery. Their products are highly configurable. She told me that every year they have 50% new configurations they have never seen before. The number of choices on their products has grown over time. ”A salesperson can’t know everything about the product,” she said. “Customers want a few choices, and before you know it, the quote has crept into a configuration that’s bad for the customer and bad for us. “
As the VP explained, the biggest opportunity for complexity management is at the point of taking an order. A customer wants to be guided to complete their order. This concept is called Demand Shaping. There are myriad ways a configurable product can be ordered. However, each customer cares only about a few features that are of high importance to him or her.
Extending the product configuration to gain insight
One of the most important components in choice complexity is the product configuration itself, the mixture of product options that give a product its unique signature. Obviously the typical product orderable options are needed to analyze the complexity of a product, but other more abstract options can offer surprising insights into product and customer behaviors.
A typical car configuration has options such as sedan, V6 engine, automatic, blue, cloth, AM/FM/CD, sunroof. But more abstract items can be recorded along with these to offer more insight. Sales type can be recorded to analyze what types of product configurations sell better in promotional sales events as opposed to normal sales transactions. An attribute to record an extended factory warranty option may provide new ideas for packaging options together with additional warranty services that customers are moving towards.
Comments Off
How many choice combinations does your product have? That depends.
Possible combinations
This is a question with several answers. The easiest answer is the least useful. The number of possible build combinations, or unique configurations, is easily computed by multiplying the number of options for each feature. For example, if your product has feature A with 3 options, feature B with 2 options and feature C with 4 options, then there are 24 (3 x 2 x 4) possible build combinations.
These numbers grow very rapidly. If you have 5 features, each with 4 options, there are about 1,000 build combinations (exactly 1,024). With 10 such features, the number of combinations is about 1 million (1,048,576), and with 15 features it is over 1 billion (1,073,741,824).
Comments Off
Key Concepts To understanding Product Variety
1. Product
A product is something offered for sale to customers. This is deliberately vague, because we want to encompass services as well as tangible products. Most of our discussion and examples involve manufactured products, but our framework also applies to services with many variants like insurance policies and cell phone calling plans.
2. Instance
An instance of a product is a specific unit of the product: the car that Joe buys, which has a specific VIN (Vehicle Identification Number).
3. Configurable Product
A configurable product is a product where the instances are not all identical. No. 2 pencils are not configurable. Computers, cars, tractors, refrigerators and cell phones are configurable.
The Root Cause of Product Complexity!
Emcien defines product complexity as simply the ability to predict what the next order coming into the company will be.
Think about it: If you only made product configuration A, you have 100% confidence in knowing that the next order in the door will be configuration A (assuming you get an order in the door at all, not a total given in this economy). But if you have configurations A and B, it’s harder to know and with A, B and C, it’s even harder, and so on. When you have thousands of configurations, predicting the next one is very difficult.
It’s not just the number of configurations that’s important but also how they’re distributed. If I have 10 configurations but 90% of my orders are for config A, then it’s still safe to predict that the next order is config A. But having 10 configs that have each been ordered 10% of the time is extremely complex!
Comments Off