Tag: choice combinations
Connect With Us
Top 3 Survival Tips for Manufacturing
1. Have visibility into what is selling
2. Streamline your product offering based on sales
3. Customize your supply chain to your product offering and demand signal (Read as “educate the supply chain of the product based on sales”)
A manufacturing operation that is disconnected from sales is bound to have high inventory and poor capital utilization – both being extremely detrimental to profitability. continue reading »
The Myth of Build-to-Order
Are You Looking At Top Selling Choice Combinations Before Stocking Inventory?
In working with manufacturers of configurable products, we have never met one that did not claim that they only build to order. “We don’t build until we have an order in hand” they all say. At first we believed them. A whole generation of companies has been transfixed by Michael Dell. No finished goods inventory; don’t assemble the parts until you know exactly what the customer wants; get the cash before you build the product.
Dell can assemble a computer in three minutes. A truck or a backhoe takes a little longer. But the same ideas should apply! Right?
Dell builds computers for final customers who come to its web site or its 1-800 phone line. Most manufacturers of expensive, complex products are once removed from their final customers. Their immediate customers are dealers. Final customers go to distributors and dealers to buy backhoes, tractors, work trucks, lighting fixtures, industrial fans, and so forth. The “customer orders” that the manufacturers so proudly wave are not final customer orders, they are actually channel/dealer orders. (Okay, this is an exaggeration, some are actual customer orders passed through by the dealers.) And how do the dealers place orders? They guess. They choose combinations of 30 or more options based on their experience. One manufacturer we worked with kept referring to these as “Christian orders”. After a while we asked them what they meant by “Christian orders”. With a big smile they said “Oh, we just take them on faith.”
So the dealers order certain product choice combinations to stock based on their intuition, and those units sit on their lots until they sell. Sure looks like finished goods inventory. There is some ambiguity about who actually owns the inventory. The manufacturer will say that the inventory belongs to the channel or dealer, so it’s not my problem any more. The dealer will say that the manufacturer finances his inventory; some cases has to take back the units and give his money back if a unit sits too long. In any case, the manufacturer knows that the dealer is not going to order any more units while his lot is full of “stale inventory” or “lot rocks”. (See Chrysler’s desperate attempt to force its dealers to accept more cars in 2008.)
So Dell computers are built to order. (And now also built-to-stock for their new retail model for stores such as Best Buy and Wal-Mart.) Jumbo jets are also built to order. But most configurable products are still a combination of build-to-order and build-to-stock, with manufacturers and dealers playing hot potato with the inventory. This means that somebody should be looking at the history of what combinations sold in the past, and trying to make sure that the stuff that they build is the stuff that sells! Looking at the sales patterns and trends is a very fast, efficient and intelligent way to determine what to carry. This is a more reliable than believing in Christian Orders or relying on dealers’ intuition. The manufacturers should be giving the dealers guidance on what to stock and order based on their global visibility into sales and customer buying trends. Customers buy combinations of features, and they do this in predictable ways. Detecting and using the patterns can make inventory turn faster, even if, technically it doesn’t exist.
Four Times the Sales Transactions With the Same Head Count!
Products have so many choices. Customers hate the experience of having to answer 50 questions to get to selection. Asking them 50 questions translates to poor customer experience and it is actually bad for you too. Here is why. Every sale begins with a customer calling out the top 3 or 4 items they want in a product. I wish there were big blinking lights that could now say “Big Opportunity!” This moment is the biggest opportunity for you to recommend a product choice that meets his needs, while being good for you as well.
In ‘days of yore’, that is what a good salesman would do. He would look over his shoulder and see what he had in stock, and gently guide the customer to one of those products. But those were the days when products were fewer, choices were fewer, and sales guys could look over their shoulder and see what they had in stock. Gone are those days! Today – sales is outsourced. It is one of the biggest and most critical functions’ that has been outsourced. Sales are done though dealerships, channels, etc. Even when a company has internal sales resources, the sales teams tend to be big or have heavy turn over. So – you have a newbie selling your product more often than not.
As product choices have continued to skyrocket, this poses a tremendous challenge on sales reps, sales channels and outside sales people. They lack the tools and automation to quickly hone in on customers’ needs and recommend product choices. The lack of these tools is causing tremendous challenges to sales people and customer. Here is a list of some of the outcomes:
- Poor customer experience due to inability to recommend good product choices at point of sale .
- Lost sale because customers do not like to answer endless questions to get to a product choice. More often than not – this is bad for the seller as well. Long list of questions result in random choice selections. This causes one-off products and poor product selection.
- Longer sales cycle – Every sales rep will tell you that he wants to recommend a good product choice and close the sale. The faster you can recommend a product, the higher the conversion rate.
Today’s sales tools and CRM include contact management and pipeline management. We do not expect the sales reps to remember the names and contact information of their customers. But why do we expect them to memorize the product features and choices? Why do we take them through endless product training sessions, even as the products are changing?
CRM needs product selection information to enable a sales rep to close the deal. Jane Barrett, Research Director at AMR presented some of the benefits, in her presentation to an SAP user group in October 2009.
Here is a short list of the benefits of empowering sales reps with guided selling at point of sale –
- Sales cycle time drops dramatically, from days to instantaneous.
- Increase in profit (2% in one case) by continuous up selling and offering alternatives at point of sale
- Four times as many sales transactions can be handled with the same headcount. (400% sales productivity improvement!)
If you do not use product recommendation tools, your sales staff is working at 25% sales productivity. In affect, you have 4x the staff you need to do the same job
Call To Action – Please talk to your sales reps and channels on how they are currently selling your product and their current challenges. If they do not have automation and tools to recommend product selection, you have a significant opportunity for improvement. A potential opportunity to improve sales productivity by 400% !
Comments Off
Do Customer Buying Patterns Exist?
Customers have to make choices in order to buy configurable products. Do they make these choices at random, or are there patterns? When we look at the sales history for a configurable product, like a car or a computer, can we tell if customers have just been flipping coins and rolling dice? Or do their choices hang together and make sense? To answer this question, we would have to look at how they buy combinations of options. In the previous post, I took a pizza as a simple configurable product, and looked at how customers ordered pairs of toppings. Just by looking at the sales numbers we could detect that the selection of pineapple and Canadian bacon are not independent. Even if we had never heard of a Hawaiian Pizza, we could discover it in the data.
Even more information is hidden in combinations of three toppings at a time, or four toppings at a time. Any combination of toppings will have appeared on some of the pizzas that have been sold (or maybe none). The relative popularities of all the different combinations has a clear message: customers are not flipping coins. Some toppings naturally go together, and others do not. Pepperoni, broccoli, and anchovies is just unlikely. If a particular pizza restaurant has a few “house specials”, like the Meat Lovers and the Veggie Delight, we can see them in the data, even if we don’t know their names.
What is true of the pizza is also true of other configurable products: computers, trucks, tractors, lighting fixtures, industrial fans, and so on. All products that have variety. Customers make choices, but not by rolling dice. There are combinations that go together and combinations that do not. A pizza maker can juggle the preferences of his customers in his head. But when a product has 30 or more features, intuition is overwhelmed. The number of combinations explodes so fast that the unaided human mind can’t see the patterns. At this point, mathematical models and intense number crunching can reveal the patterns and let the product manager for a line of trucks be as confident as a pizza maker.
Do Customer Buying Patterns Exist?
Buying patterns are real, and they manifest themselves in how customers buy combinations of options. With the computing power we have available today we can detect and capture them. These patterns can then be used to design “house specials”, forecast future sales, and guide customers to what we want to sell them.
So, who else is talking about customer buying patterns?
Intel Talks about Changing technology buying patterns
Customer Buying Patterns have Changed. What’s Your Plan?
An entire report that summarizes the results of a consumer usage and purchasing pattern survey conducted in March of 2007. The survey was conducted with In-Stat’s Technology Adoption Panel (TAP) — a dynamic, online panel of more than 19,000 technology users and decision makers. Over 1,400 technology users responded to this focused survey.
Findings in this report include consumers’ time spent on PCs, when they last purchased a personal-use PC, the PC’s features/form factor/usage, the desired features of future PC purchases, changes in usage patterns, and consumers’ thoughts about new technologies.
The changing patterns include -
- When consumers are likely to make their next PC purchase.
- The features consumers state they want
- The features consumers state they really want, based on changes in their usage/buying patterns.
- How consumers view new technologies
However – buying patterns are constantly changing. As social networking grows, we are watching new markets emerge every day. There is gold for companies who can continually detect these patterns and offer the right products and feature mix.
Customer Buying Patterns – What you can learn From Pizza Sales
There are 1,140 ways of ordering a pizza with 3-toppings, if the pizza offers 20 choices
First order take rates tell us about the relative popularity of different options. For example, consider a small set of possible pizza toppings.
|
Topping |
Take Rate |
|
Pepperoni |
40% |
|
Mushrooms |
20% |
|
Pineapple |
3% |
|
Canadian Bacon |
3% |
|
Green Peppers |
10% |
Customer buying patterns really start with second order take rates, which tell us about pairs of options, or toppings. Second order take rates tell us about relative popularity, but they also reveal something deeper: dependence. If you know that a pizza has pineapple on it, there is a very good chance that it also has Canadian bacon. This is dependence. In this case the reason is that there is a widely known “Hawaiian Pizza” that has both of these toppings. In general, customers don’t flip coins or roll dice. They select options that “hang together” in some way. The patterns can be seen in the combined take rates. Let me illustrate with three examples that are contrived to illustrate some important points. First consider pepperoni and mushrooms together.
|
|
|
Mushrooms |
|
|
|
|
No |
Yes |
|
Pepperoni |
No |
18% |
12% |
|
Yes |
32% |
8% |
|
In this table you can see that pepperoni has a 40% take rate, since 32% of pizzas have pepperoni without mushrooms, and 8% have pepperoni with mushrooms. In the same way, 20% have mushrooms, because 12% have mushrooms without pepperoni and 8% have mushrooms with pepperoni. This illustrates the first law of second order take rates: the first order take rates must be preserved. But this table contains no new information. Customers are apparently ordering pepperoni and mushrooms independently. This is revealed by the fact that 8% is exactly 20% of 40%. Knowing that a pizza has pepperoni does not give us any clue about whether or not it has mushrooms. Similarly, knowing that it has mushrooms is useless in guessing if it has pepperoni.
As a second example, consider the two toppings that are on every Hawaiian pizza: pineapple and Canadian bacon.
|
|
|
Canadian Bacon |
|
|
|
|
No |
Yes |
|
Pineapple |
No |
97% |
0% |
|
|
Yes |
0% |
3% |
For simplicity, I have made this an example of complete dependence: a pizza has pineapple if and only if it has Canadian bacon. Notice that the first order take rates (3% for each) are preserved.
The third example is the really important one: partial dependence. This is illustrated here by pineapple and green peppers.
|
|
|
Green Peppers |
|
|
|
|
No |
Yes |
|
Pineapple |
No |
89% |
8% |
|
Yes |
1% |
2% |
|
In this case, the first order take rates are also preserved: 3% for pineapple and 10% for green peppers. But these two choices are not independent. The take rate for pineapple and green peppers together is 2%, which is much greater than 10% of 3%, which would be only 0.3%.
Exercise for the reader: show that if we know that the pizza has green peppers, then there is a 20% chance that it has pineapple. (Much greater than its 3% first order take rate.) And if we know that it has pineapple, then there is a whopping 67% chance that it has green peppers!
So second order take rates capture information about how customers are combining toppings, and we can use that information to make predictions.
Comments Off
True Demand Intelligence – Knowing who is buying what, where and why
Demand Intelligence – Knowing Who is Buying What, Where and Why
SKU numbers are an easy way to keep track of items that are built, stocked and sold. The SKU number itself is arbitrary and contains no ‘intelligence’.
The SKU number was invented for a very good reason. When this practice started, the number of SKU’s was small, and people and systems needed a simple way to track what they had. So ASP-678 may be the SKU number for a toothpaste tube with spearmint flavor, whitening, and tartar control. However, customers do not look for SKUs. They look for toothpaste with whitening, tartar control, flavors, sizes, etc. Customers buy attributes, and combinations of attributes. Some companies code the attributes into the SKUs, by concatenating two or three character codes (like SPWHTC). But this is at best a clumsy way of handling a few attributes. Companies want to know what attributes customers are looking for, and SKU numbers hide the attributes.
As the number of attributes starts to grow, whether you have them coded into the SKU number or not, the problems start to mount! The most important one is that companies do not know what customers are buying, or trying to buy. As the number of choices grows, the number of combinations grows much faster and companies drown in their own SKUs.
SKU intelligence is going behind the SKU numbers and ‘detecting what attributes customers are buying’. Knowing who is buying what, where and why is “True Demand Intelligence”.
Products have attributes. For example, a computer has a processor, a memory, and a hard drive. For each attribute there may be several alternative choices. This means that there are many different product configurations. Some companies make only a fixed subset of all the possible configurations and give each one a SKU number. Other companies allow customers to order exactly what they want, and if this is something new, then they create a new SKU number for it. In either case, a SKU number is supposed to represent a unique product configuration.
If you are trying to figure out what your customers want, then SKU numbers are a form of encryption. You have to look at your sales history in terms of the underlying attributes, and the choices for those attributes. Instead of looking at one SKU number you need to look at perhaps 20 separate attributes. The SKU number is a way of collapsing those 20 dimensions into a single dimension, with tremendous information loss. One of the things that is lost is proximity to other SKU’s, based on attribution. A customer who bought SKU A-1234 might have been satisfied with (or really looking for) SKU B-3728. These two SKUs have the same choices for 18 of the 20 attributes, and differ on only two. This is obvious when the unique configurations are represented as a set of attribute choices, but hidden when they are represented as SKU numbers. The first step in analyzing a sales history has to be expressing it in terms of the underlying attributes. Each SKU number has to be expanded into a list of choices. Then we can begin to find patterns in how the choices are made. The leather seats and the DVD player are usually bought together. Engine block heaters are not ordered on convertibles. Buying patterns exist at the attribute level, not at the SKU level.
“Buying patterns” are popular combinations of attribute choices. These can be pairs of attributes, triples of attributes, or even more. Popularity is measured by the share of sales that have that combination. Buying patterns are helpful in selling, because they reveal how customers can be moved to configurations (SKUs) that we have in stock, or that we would prefer to build. Experienced sales people are skilled at moving customers, but If these patterns are represented in some kind of knowledge base, then a computer can make the recommendations.
Customers also have attributes. The simplest is perhaps geographical location. There are patterns that involve both product attributes and customer attributes. Customers in Florida are more likely to buy convertibles; customers in North Dakota are more likely to buy engine block heaters. Customers may have several attributes, for example demographic attributes for individuals or industry attributes for companies. (We don’t assign SKU numbers to customers!) If your sales history contains information about the customer as well as information about the product, then we can look for buying patterns that are associated with certain kinds of customers.
As an example, for a desktop computer the list of attributes might be: Processor, Memory, Hard Drive, Keyboard, Monitor, Mouse, CD/DVD, Application. A specific SKU number like A-1234 is a code for a specific configuration, say (2GHz, 2GB, 120GB, Ergonomic, 22” flat panel, Wireless, R/W Combo, Gaming). The Application attribute is really a customer attribute, with values like Home, Small Business, or Entertainment, as well as Gaming. This would make it possible to look for typical Gaming configurations and typical Entertainment configurations.
SKU numbers are a useful shorthand for record keeping. Each SKU number represents a unique product configuration. But analyzing SKU numbers is like analyzing telephone numbers. To see the buying patterns, you have to go to the attribute level. The patterns exist among the attributes, so you have to decode the SKU numbers to see them.
What does the stairway to complexity tell us?
If a product is too complex, where is the complexity coming from? Which features are causing the explosion in the number of build combinations? The stairway to complexity tells us where to look.
The stairway to complexity shows how the number of unique configurations drops as features are removed. Here is another stairway for a backhoe with 30 features.
The number of build combinations drops from 934 down to 1 as we remove the features. Behind the graph is the actual list of features in the order they were removed. In the table below, the features are ranked from 1 to 30, corresponding to the steps in the graph.
If we want to simplify our product, this ranking of the features tells us where to start. The greatest contributor to complexity is the Buckets, of which there are 34 different kinds. The number of build combinations would drop from 934 to 838 if we didn’t have to worry about Buckets.
Is the ordering of the features in the stairway the same as the ordering by number of options? The first feature in the stairway is certainly the one with the most options (34). But Tran_Control has the second largest number of options (9), and doesn’t appear in the stairway until step 15. So there is more going on than just the number of options.
The amount of complexity introduced by a feature depends not just on the number of options, but on the relative popularity of the different options. Having two options that are split 50% to 50% is much worse than if they are split 90% to 10%. (See earlier post: Entropy of a coin toss.)
Introducing a new feature only increases product complexity if it splits existing configurations that would otherwise be the same. One manufacturer insisted that his product was so complex because it was produced for many different countries. But the number of unique build combinations was exactly the same whether the Country feature was included or not.
Comments Off
Stairway to (Product) Complexity (a.k.a. Why Do I have SO Much Stuff!!!)
In the last post I introduced two ideas about the sales history of any product. First, the number of unique configurations, or build combinations, depends on which features are included in its description. Second, the number of unique combinations drops whenever a feature is removed. A natural question to ask at this point is: Which feature, if it were removed, would lead to the greatest decrease in the number of unique configurations?
This is an easy question to answer, if we have a way of counting the number of unique configurations in any input set of configurations. This is really just a matter of sorting, so suppose we have such a counting algorithm. We try removing the features, one at a time. In each case we apply our counting algorithm to get a score. The score is the number of surviving unique configurations. The feature with the lowest score is the winner (like golf).
Now suppose that we permanently remove the winner, and repeat the contest again. This will determine a second winner, which can also be removed. We keep repeating until there are no features left. Now imagine a graph with the number of features removed on the x-axis and the number of surviving unique configurations on the y-axis. This is the stairway to complexity.
The stairway shown above is for a product (commercial stoves) with 23 features. The number of unique configurations starts at 1223 and drops to just 1 as the features are removed. The features are removed by looking for the biggest drop at each step.
Abstract:
Product complexity is driven by large number of options. Companies struggle to determine which feature choices are driving complexity. They typically “randomly cut choices” to streamline and rationalize SKUs. The cost of product complexity is tremendous on engineering. The current PLM systems do not have a method to measure this and provide intelligent feedback to engineers on how to standardize platforms to reduce engineering and maintenance costs. This article clearly details the metrics around product complexity and how to solve this issue.
Comments Off
The Number of Choice Combinations Depend…
The number of choice combinations depend on which product features are included. The build combinations is the product mix or the marketing mix.
Let’s consider the sales history of our product. There are two very important numbers: the number of units sold and the number of unique configurations. The number of units is well defined, but the number of unique configurations is ambiguous. The ambiguity comes from the fact that there will be more unique configurations if we use more features, especially soft features, to describe our product.
One very special soft feature is a Serial Number, or VIN (Vehicle Identification Number). The whole purpose of the Serial Number is to make each instance of the product unique. So if we look at our sales history and include Serial Number, we will see that the number of unique configurations is exactly the same as the number of units of the product (instances).
If we want to begin to understand the demand for our product we have to see which instances are actually the same. That means we have to get rid of the Serial Numbers. When we do, the instances collapse into groups of now unique configurations; that is, unique without Serial Number.
If we are interested in the tangible features of the product, then we may want to take out other soft features as well. Geographic region is important for some purposes, but may be a distraction when we are interested in the physical product. Taking out the geographic region feature will cause another reduction in the number of unique configurations. The red, V8, convertible in Florida will get combined with the red, V8, convertible in New York.
Sometimes we are interested in the variants of our product ignoring color. We know that every real variant is going to come in several colors, but we want to look at the product without the distraction of color. This is sometimes called the “body in white”. So the red, V8, convertible and the green, V8, convertible collapse into the V8, convertible.
The point I am making is that the number of unique configurations depends on which features are included, and this number drops whenever a feature is taken away. Mathematically, this is called “projecting out the feature”.
The number of unique configurations is at most the number of units sold, and at a minimum it is just one. If we take away all of the features, then every unit looks the same, which means just one configuration. There is a path from one extreme to the other that we will introduce next time.
By the way – understanding this is important as product complexity is a key driver of process complexity.
Comments Off
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