Too much information for forecasting?

Mike Gilliland
Mike Gilliland|May 15, 2012

First: A Report from the 67th Pine Tree Festival and Southeast Timber Expo

Back in March The BFD investigated the topic of Google-ing yourself (aka egosurfing). I reported on finding a namesake in show business, a self-described "Magic Mike Gilliland" and his sidekick Lollipop the Clown.

I attempted to disparage Magic Mike by claiming I first heard about his act in the documentary, The Aristocrats.  Apparently the decency-loving folks of Swainsboro, GA weren't paying attention, and let Magic Mike appear as planned at the 67th Pine Tree Festival and Southeast Timber Expo.1  Now, much to my further dismay, Magic Mike's act received a very favorable review on MySwainsboroNews.com:

Magic Mike Gilliland ... wowed kids of all ages with his feats of illusion mixed with healthy doses of comedy. Between shows, Gilliland and his sidekick, Lollipop the Clown, entertained festival goers with even more magic and laughs.

This was crushing news -- I always thought I was the funny Mike Gilliland.

Is this Too Much Information for Forecasting?

Consumer Goods Technology recently posted an article by Joe Shamir of ToolsGroup,  "Data, Data, Everywhere...But Most Manufacturers aren't Using It To Improve Forecasting." I generally agree with Joe's point that there are readily available sources of data we aren't taking full advantage of. (Point-of-sale data may be a prime example.) However, I did find myself disagreeing with Joe's discussion of the value of line-orders (individual customer orders for specific items).

We typically look at sales history at some level of aggregation, such as all sales of item X at location Y over some time period like week (or month).2  We utilize this aggregated history to forecast future demand for item X at location Y by week (or month).

For inventory planning purposes, forecasts are best accompanied by some indication of confidence or uncertainty. If demand patterns are fairly stable and predictable, and the forecast is for 100 +/- 10 units, this could lead to much different inventory practices than if the demand patterns are volatile and the forecast is for 100 +/- 100 units.  In the former situation we should be able to maintain high customer service (i.e. order fill rate) with less inventory than in the latter case.

I think this is the direction Joe is going when he advocates digging below the aggregate data (item / location / week level) to investigate the individual line-orders that make up the aggregate data. He argues, correctly I believe, that the statistical behavior of demand will be different, depending on the line-order makeup of the aggregate data.

For example, I would agree that if an aggregate of 48 units for an item / location / week is made up of just one order (for 48) units, the volatility of this demand stream would likely be higher than if the aggregate 48 were made up of many smaller orders. And I totally agree with the implication that demand volatility has a big impact on our ability to forecast accurately, and on how much inventory will be required to maintain service levels.

My disagreement is with the extra effort of examining the line-orders -- I don't understand why this is necessary. Why do I need to care about individual orders? Whatever volatility there is in demand will manifest itself in the aggregate (item / location / week) data!

If the line-orders are mostly single large orders and cause a more volatile demand stream, then I'll see this in the aggregate data.  If the line-orders are mostly small orders and result in less volatile demand, I'll see this in the aggregate data. I'm struggling to find the value in analyzing line-orders when I can get all the relevant information I need from the aggregate (item / location / week) data.

In short, the underlying message on the importance of demand volatility is sound. But line-orders, I believe, are TMI.

------------------------

1Congratulations to Jacob Ellis, winner of the Pine Tree Festival slogan contest for his poetic "200 years of the amazing pine / have made Emanuel County fine." I haven't heard a flow like that since 50 Cent's "What Up Gansta?"  Jacob must have some Longfellow in him. Maybe he can move to Michigan and join D12 (aren't they frequently down a member?).

2Time-series forecasting models use bucketed data -- individual transactions that have been accumulated into equally spaced time buckets such as weekly or monthly. SAS forecasting software includes simple methods for accumulating transactional data into appropriate time buckets.

Post a Comment

Guest Blogger: Len Tashman previews Spring 2012 issue of Foresight

Mike Gilliland
Mike Gilliland|May 8, 2012

Pet lovers do the most incredible things. My friend Grace told me she trained her pet rabbit to walk on a leash. I said, "That's amazing Grace -- I never heard of such a thing!!! I thought rabbits could only hop."

Rest assured there are no dogs (cats or rabbits either) among the articles in the Spring 2012 issue of Foresight.

Editor Len Tashman's Preview of Foresight

This Spring 2012 edition of Foresight marks our 25th issue since the journal’s inception in the summer of 2005. It’s also the 10th anniversary of the awarding of the Nobel Prize in Economic Sciences to Daniel Kahneman. Kahneman was ecognized for his pathbreaking insights on the not-always-rational ways in which we make our predictions and reach our decisions. Now, in his book Thinking, Fast and Slow, Kahneman presents the capstone of his work and its implications for improving our performance as analysts and forecasters. Reviewer Paul Goodwin concludes that any forecaster who uses judgment in his or her methods will benefit from reading it.

Robert Fildes and Paul Goodwin offer Foresight readers a set of Guiding Principles for the Forecasting Support System. FSS refers to the process-hardware-software infrastructure that produces the operational forecast and permits managerial adjustments to statistical forecasts. These guiding principles offer a valuable checklist for firms seeking to evaluate and upgrade their software solutions, as well as fortifying organizational support for the forecasting function.

How often do you see an article that reveals our missteps as forecasters?* Well, Foresight’s Joe and Simon Sez column in this issue attempts to backfill this gaping void with the dynamic duo’s admission of Our Best Worst Forecasting Mistakes. “Inadequate reporting” is one, “Failure to create benchmarks of success” another, with “Assuming that the raw data were correct” adding insult to injury. But the very best may be “Failure to prepare stakeholders for change.”

Our section on Forecasting Principles and Methods includes three articles. Roy Batchelor examines the benefits and foibles of Prediction from Patterns. Past occurrences of an event often serve as analogies for forecasting the impact of the new occurrence. The reliability of the analogy, Roy tells us, lies in the proper balance of data interpretation and good judgment. But applying only one of these without the other can result in a “bad pattern.”

Scott Armstrong follows with a discussion of the Moneyball Factor in predicting personnel performance for hiring decisions. Many of you have read the book or seen the movie. Scott liked the message, expands on it, and tells us about his attempts to convince organizations that it’s a message worthy of their consideration.

Rogelio Oliva and Noel Watson wrap up this section with their commentary on Steve Morlidge’s “The Forecasting Process: Guiding Principles.” Their focus is on the sources of organizational bias, and they offer their recommendations for Designing the Forecasting Process to Manage Bias.

Foresight's S&OP Editor Bob Stahl teams up with former APICs president Joe Shedlawski to reveal a major S&OP “catch-22” (“damned if you do and damned if you don’t”). Their article is Executive S&OP: Overcoming the “Catch-22” of Implementation. If top management is involved with S&OP implementation from the start, the changes successful  implementation requires may cause organizational and executive discomfort; but failing to involve top management  undermines chances of the project’s success. The authors present a convincing path out of the dilemma.

Our 25th issue concludes with Roy Pearson’s latest Forecasting Intelligence column, Forecasting for Fun Outside Your Cubicle. It’s about having some fun at the Forecasting World Events website while at the same time “helping the nation’s intelligence community to advance the science of forecasting.”

----------------------

*If you like "Our Best Worst Forecsting Mistakes," you might also be interested in:

Post a Comment

Are you an Analytic Superhero?

Mike Gilliland
Mike Gilliland|May 4, 2012

Have you seen this week's news item on "tanning mom" Patricia Krentcil, the New Jersey mother accused of sunburning her young daughter in a tanning booth?

Now I'm as big a fan of diversity as the next guy, and lovingly embrace people of every visible color (although I do find House Speaker John Boehner's  orange a bit frightening). However, this lady is too much. She is like George Hamilton squared. I've seen a more humanlike complexion on a copper roof.

Apparently Ms. Krentcil is a victim of "tanorexia" so I probably shouldn't be so harsh. But sheesh, didn't Magda the neighbor lady in "There's Something About Mary" teach us anything?

What's really irksome is how much she spends on this selfish, loathsome, and unhealthy habit ($100/month per news reports), and only shares it with one child!!! (I hate a mother who picks favorites.)  For that kind of money she could buy a couple of cartons of Lucky Strike and share them with all five of her kids.

I wouldn't date tanning mom with a carbon radioisotope.

Announcing the League of Analytic Superheros

We aren't talking Agent Orange and Copper Philiac (alter-egos of the above mentioned Mr. Boehner and Ms. Krentcil), or even MC Hammer.

Bill Franks aka Dr. Insight

We are talking about the SAS and Teradata launch of the League of Analytic Superheroes – a talent search for best-of-the-best individuals, teams and companies who are masters of integrating analytic solutions from SAS and Teradata to produce earth-shattering insights and tangible business value.

The first two analytic superheroes were unmasked at SAS® Global Forum in Orlando, FL last week. The leader of the illustrious League is Chief Analytics Officer Bill Franks of Teradata, aka Dr. Insight. Joining Bill was Rick Andrews (aka Illumino), who works in the Office of the Actuary for the Centers for Medicare and Medicaid Services.

Rick Andrews aka Illumino

Do you have analytics superpowers?   If so, you could be honored at an upcoming SAS or Teradata event, and immortalized with a graphic illustration and action figure in your superhero likeness.

Tell us your story.  The League needs you.

(See my colleague Shannon Heath's SAS Voices blog for a full account of the unveiling.)

Post a Comment

Incorporating demand planner knowledge

Mike Gilliland
Mike Gilliland|May 3, 2012

Can you explain the "random error" in your forecasts?

This question was posed two weeks ago by Sam Iosevich, Managing Principal at Prognos, during his presentation  at the INFORMS Conference on Business Analytics and Operations Research. Sam stated that if your planners have knowledge that helps explain the "random error" in your forecasts, then that error is not completely random, and such knowledge should be incorporated into your forecasting model.

Incorporating Demand Planner Knowledge into the Statistical Forecast

In his book Demand-Driven Forecasting (pp. 6-7), my colleague Charlie Chase asserted that "...there is no art to forecasting, but rather statistics and domain knowledge." He argued that we cannot turn a gut feeling into a number, but instead must "...access the data and conduct the analytics to validate [our] assumptions."

Charlie, like Sam, is avowing a scientific approach to forecasting: develop a hypothesis, find the data, and conduct the analysis to determine whether you can reject the hypothesis. The results are then used to adjust the statistical forecast, or better yet, "...build those assumptions into the statistical baseline forecast by adding the additional data and revising the analytics."

In his presentation, Sam showed there are two types of domain knowledge:

  • Explanative -- insight into a demand anomaly in the past.
  • Predictive -- insight into the future which may or may not have historical precedence.

For example, a flood (or other natural disaster) or competitive activity in the past can be modeled to help establish the "true" baseline demand in the historical period. This is "explanative" domain knowledge.

Past (and planned future) promotional activity can be modeled to establish the baseline historical demand (and promotional lift), and be incorporated into future forecasts. This is an example of "explanative and predictive" domain knowledge.

Sam points out the benefits of properly incorporating domain knowledge:

  • Increase statistical vigor
  • Reduce Judgmental overrides
  • Eliminate organizational bias
  • Facilitate mathematical optimization of supply chain planning

To achive this is a four step process:

  1. Identify - Not all Domain Knowledge can or should be modeled.  Ask organization which factors effect demand, and then evaluate the effort vs. potential benefit or statistically modeling
  2. Model - Capture test data and create statistical model
  3. Evaluate - Validate that results including Domain Knowledge model add value to the forecast
  4. Imbed - Incorporate capturing value add domain Knowledge into the Demand Planning Processes, and model statistically

For more thorough explanation and details of this approach, you can reach Sam at sam.iosevich@prognosinc.com.

 

Post a Comment

The numbers behind burgers and fries

Mike Gilliland
Mike Gilliland|April 27, 2012

Last week's INFORMS Conference on Business Analytics and Operations Research drew over 700 attendees to Huntington Beach, CA. I had the pleasure of serving on the conference selection committee, and wanted to share this content from one of our invited speakers, Kean Chew of HAVI Global Solutions.

The Numbers Behind Burgers and Fries: A Holistic and Dynamic Single View of Demand

HAVI provides analytics and supply chain services to companies such as McDonald's (with almost 14,000 US locations). If supply chain management were simple, then major corporations wouldn't need the professional services of HAVI -- but they do. This is because supply chains can be easily disrupted in two kinds of ways:

Uncontrollable Disruption: Earthquake, tsunami, fire, hurricane or other natural disaster.

Controllable Disruption: Marketing promotions.

Kean summarized his presentation with these bullets:

  • Goals of supply chain is to have the right products at the right place, time, and cost. The goals are the same regardless of industry (e.g., Quick Service Restaurant, retail, and big box stores). Does not matter if we are talking about burgers and fries, jeans and shirts, or toilet paper and laundry detergent.
  • The journey to achieving supply chain utopia sounds simple but are quite elusive because of speed bumps, roadblocks, detours, and other surprises along the way.
  • Disruptions, or speed bumps, include natural disasters (e.g., tsunami in Japan last year and Hurricane Katrina a few years ago).
  • Disruptions are also caused by marketing promotions. With marketing promotions, it is no longer business as usual (e.g., BK’s BOGO, Denny’s free Grand Slam, and McDonald’s use of promotional packaging materials). When not well managed, marketing promotions can feel like disasters, which are exacerbated in a supply chain ecosystem that has many parts and players.

To emphasize this point, he brought up the interesting case of a "promotion gone awry" when KFC offered a free grilled chicken meal in 2009, which they had to retract:

"Following an unprecedented and overwhelming response...KFC has announced that it can no longer accept the free coupon..." (KFC press release, May 7, 2009)

[SIDE COMMENT TO READERS: KFC grilled chicken is really really good, so I can understand the overwhelming response. I just wish my local KFC restaurant weren't out of grilled half the times I go there.]

[SIDE COMMENT TO KFC MANAGEMENT: Perhaps you ought to let HAVI start managing your supply chain so my local KFC restaurant will stop p****** me off.]

Kean points out that when asked, different entitites in the supply chain ecosystem will recommend/provide different production numbers to support a marketing program. He describes this as akin to the cartoon about describing an elephant from different vantage points.

  • Promotions introduce volatility and uncertainty to the supply chain ecosystem. For supply chain to have a fighting chance of success to support marketing promotions, the whole ecosystem has to subscribe to a single view of demand (hence the holistic part of the title of the presentation).

Finally, Kean utilized a "waterfall chart" to create a more holistic view of demand. Different industries will have different building blocks in the chart, but they commonly include things like "single view of demand," "system inventory," "safety stock requirements," and "promotional lift."

  • As marketing plans are likely to change throughout a promotional lifecycle, it is important to be dynamic by updating the single view of demand. Examples: When there are additional media planned, price discounts, mobile coupons, and the like.
  • During the promotion it is also important to be dynamic by steering and shaping demand -- especially when demand comes in higher/lower than expected. To enable this would require visibility and revisions to the single view through reforecasting/recalibration.

For more information on this presentation and approach, you can contact Kean directly at kchew@havigs.com.

Post a Comment

Forecasting and analytics at Disney World

Mike Gilliland
Mike Gilliland|April 23, 2012

The April 2012 issue of ORMS Today contains a piece on "How analytics enhance the guest experience at Walt Disney World," by Pete Buczkowski and Hai Chu. While many of us are used to forecasting just one or two things (such as unit sales or revenue), Pete and Hai illustrate the very many areas where forecasting drives the operational planning at Disney:

  • Park attendance -- for strategic planning and setting park hours.
  • Guest arrivals at hotels -- for staffing the front desks.
  • Costume requirements -- for  more than one million garments used by cast members (worn, then laundered and placed back in inventory).
  • Attraction wait times -- to manage standby lines and the FASTPASS system.

The Disney labor demand planning system generates forecasts for every 15 minute period at locations throughout the property (including entry turnstiles, restaurants, and merchandise locations). This level of granularity allows the appropriate level of staffing to be available (by location and time period) to ensure guest service standards are met.

The Value of Forecasting: To Make Better Decisions

The article expands upon a point we heard just two weeks ago in Jain and Malehorn's new book Fundamentals of Demand Planning & Forecasting, that "forecasts have no value if they are not accepted and used" (p.300). As Pete and Hai put it, "While accurate forecasting is important, the results are only valuable when utilized to make smarter decisions."

They go on to show how other areas of analytics, such as data mining, optimization, and simulation are used in unique ways. For example:

  • Data mining and optimization help understand what vacation packages are most appealing to different types of guests, so that the Disney website and call center agents can offer a more customized vacation planning experience.
  • Simulation provides a virtual environment for analysis of bottlenecks and capacity in operational settings (like attraction lines, restaurants, and hotel front desks), so impact can be evaluated before doing any physical or process changes.

In Disney's analytical culture, as it should be everywhere forecasting or other analytical methods are used, improvement in decision making is the key. This is more than just some fun mathematical exercise for the analyts. It is applying what we can learn from the analysis to operate more effectively (and profitably), and making our customers happier.

Post a Comment

Ready - fire - aim

Mike Gilliland
Mike Gilliland|April 12, 2012

Are you a prefectionist when it comes to forecasting, or any kind of data analysis? If so, perhaps my SAS colleague Gary Cokins can cure you.

Gary is a prolific writer and contributor in the performance management field, and describes himself as a "ready-fire-aim" kind of guy. By this he means that he can stop analyzing when the information is good enough to gain insights or make decisions.

In a blog post "The Perils of Analysts Demanding Perfection and Precision" on AllAnalytics.com, Gary argues that speed and agility trumps slow and deliberate study, and I tend to agree. In forecasting you cannot expect perfection, so why knock yourself out pursuing the unachievable?

The value in a forecast, or any other type of analytical endeavor, is to discover something that helps us make better decisions and achieve better outcomes. The value is in the improvement. But we have to be reasonable and balance our efforts with the likely payback.

As in the Accuracy vs. Effort  chart, a little extra effort may deliver most of the achievable benefits. While a lot of extra effort may deliver very little incremental value.

Less than perfect analysis does not mean it should be "flawed, misleading, or indefensible." This is not an apology for careless work. Rather, the message is that "perfection can be the enemy of the good," improvement is the key, and just being better is often good enough.

Post a Comment

New forecasting book by Jain & Malehorn

Mike Gilliland
Mike Gilliland|April 11, 2012

Being a Hollywood celebrity means plenty of perks in addition to willing groupies. For example, the 2012 Oscars Nominee Gift Bag (valued at over $62,000) included a 5-day elephant safari in Botswana ($15,580), Eminence organic body scrub (with virgin coconut oil and raw sugar cane, $48), Naughty Bits Brownies ($50), and a year of unlimited blowouts at JM Blowdry (Beverly Hills' newest and hottest blowdry salon, valued at $2000. See these video testimonials by satisfied customers John E. and Newt G.) 1

The swagbag also included a $9.95 portion of Vaportrim, "the world's first zero calorie dessert."  Per the website:

Vaportrim is the newest scientific breakthrough in vapor technology. It works  with the senses of taste and smell so that users feel full and eat less.  Research has shown that 70-75% of what people taste comes through smell. With Vaportrim, as the vapor is inhaled, smell and taste receptors send messages to  the brain which release hormones that tell the body it’s full.2

New Forecasting Book

While not yet a Hollywood celebrity, I received my own version of an Oscar Gift Bag this week in the form of a signed copy of Fundamentals of Demand Planning & Forecasting by Chaman Jain and Jack Malehorn.

Dr. Jain is a founder of the Institute of Business Forecasting, longtime editor of its Journal of Business Forecasting, and Professor of Economics at St. Johns University.

Jack Malehorn is Assistant Professor of Economics at Georgia Military College, and contributes a quarterly economic forecast article in JBF.

The two have combined to produce a comprehensive companion for the practicing business forecaster, covering fundamentals and the forecasting process, forecasting data and modeling, performance metrics, communicating forecasts, and (my favorite) worst practices.

The communicating section includes lists of specific rules for reporting, presenting, and "selling" your forecasts to the organization. This may be the most important part of the book. It emphasizes the practice of consistency and diplomacy in the forecasting communication process. A standard, consistent report format (with graphs preferable to tables, and readily understood metrics) helps convey the results without wasting time explaining (and arguing about) the calculations. Overly complex or confusing metrics just foment the distrust that already exists around the forecasting process and forecasters in general.

Jain and Malehorn also suggest conveying the concept of forecastability, so management understands why some products are inherently easier to forecast than others. I would go beyond this to suggest ways for management to improve forecastability, for example by eliminating the incentives that encourage customers to have unpredictable demand. (Remember the Aphorism: The surest way to get better forecasts is to make the demand forecastable.)3

Ultimately, a forecast is of no value unless it is used to make better decisions and improve the organization's performance. "So, forecasters not only have to produce good forecasts but also know how to sell them" (p.300). To find out how, order Fundamentals of Demand Planning & Forecasting on the IBF website.

-----------------------------

1Who needs the comfort and convenience of blow-drying your hair at home, when you can drive across town and spend $2000 having it done by a professional?

2At first I thought this "scientific breakthrough in vapor technology" was implausible. Haven't we always been taught that inhaling just gives a person the munchies? But then I found two counterexamples:

  1. Bill Clinton never inhaled, yet has always battled his weight.
  2. Has anyone ever seen a fat Rastafarian?

I even searched Google Images for "fat Rastafarian" yet (with 35,600 hits!) still came up empty.

(Page 1 of the search did, however, yield images of a dog, cat, orangutan, and sheep with dreadlocks, along with a marble statue of a ripped Zeus(?) with the caption "My abs block arrows for breakfast."  Note to Google: You may want to tweak your search algorithm a bit.)

So Vaportrim must really work!  QED

3Even if you don't believe me, perhaps Peter Drucker's "The best way to predict the future is to create it" can convine you.

Post a Comment

Preview of INFORMS Conference

Mike Gilliland
Mike Gilliland|April 6, 2012

The INFORMS Conference on Business Analytics and Operations Research kicks off April 15 in Huntington Beach, CA. I had a chance to preview a presentation by Glenn Bailey, Sr. Director of Operations Research at Manheim (the $3B wholesaler auto auctioneer). Glenn's talk is on "The Need for Speed: Responsive Predictive Analytics," and he makes an important statement:

There's no correlation between Analytic Complexity and Business Value -- so conduct your analytics accordingly

We are in an age of amazing possibilities when it comes to the big data at our fingertips, and the high-performance analytics available for extracting knowledge and improving decisions. The technology lets us attack more types of problems, approaching them from different angles with more methods, and to do all this in much less time than it ever took before.

While the availability of this technology is a blessing, and our love of the technology is much deserved, we mustn't lose sight of the business problems we use this technology to solve. And, as Glenn asserts, we mustn't lose sight of the business value we are attempting to deliver.

For example, it is well-established in forecasting that simple methods can, and frequently do, perform better than more complicated methods. A moving average or simple exponential smoothing will be the most appropriate forecasting model in some situations, and there is no shame in that. While more complex or sophisticated methods can always give our model a better fit to history, this does does guarantee better forecasts. (See Makridakis, et al, Forecasting Methods and Applications (pp. 526-527) for a brief but excellent discussion of simple versus complex methods.)

Supply Chain & Forecasting Tracks

While at INFORMS, some other noteworthy presentations include:

 

 

Post a Comment

Editorial comment: Forecast accuracy vs. effort

Mike Gilliland
Mike Gilliland|March 30, 2012

Let's end 2012-Q1 with a graphic editorial comment:

Forecast Accuracy vs. Effort

Using a naïve model will achieve a certain level of forecast accuracy. That accuracy may be high if the demand is smooth and stable, or low if the demand is erratic. But you achieve this level of accuracy with virtually no cost or effort.

By using good forecasting software that provides automatic modeling, you should achieve better forecast accuracy with slightly more cost and effort. If you have access to more sophisticated forecasting software along with a skilled analyst to fine-tune your models, you may be able to achieve even more accuracy, but with much more cost and effort. If these are important, high-value forecasts, then the extra cost and effort can be worth it.

For example, if you are a retailer selling the latest $5000 TV, you want that forecast to be as accurate as possible because mistakes are expensive. You don't want to forecast too low, carry too little inventory, and miss sales opportunities. Yet you don't want to forecast too high, fail to hit revenue projections, and be stuck with excess inventory.)

On the other hand, if you are a hardware store selling inexpensive nuts & bolts, you don’t need to worry too much about accurate forecasting of these items because there is very little financial impact. You can rely on simple inventory management policies (e.g. two bin system) to keep from going out-of-stock and annoying your customers.

Turning now to the left side of the chart, we find that the extra effort of making manual overrides actually makes the forecast worse in many situations! (Of course, manual overrides aren't always non-value adding, but they are often enough to keep this consideration in mind. See this discussion of research by Fildes and Goodwin.)

If you have reasonably stable demand and are getting usable forecasts from your automated statistical modeling, then there may be little need to provide manual overrides. Human judgment can then be utilized only when necessary, such as for new item forecasts, or when there has been some fundamental structural change in the demand pattern that the computer system does not yet know about.

Finally, if you want to get really bad forecasts and spend a lot of company resources doing it, let executive management have final approval of all your forecasts! This is the message that Fred Torbert conveyed in his Deadly Sin #5: Senior Management Meddling.

Post a Comment

  • About this blog

    Michael Gilliland is a longtime business forecasting practitioner and currently Product Marketing Manager for SAS Forecasting. He initiated The Business Forecasting Deal to help expose the seamy underbelly of the forecasting practice, and to provide practical solutions to its most vexing problems.

  • Subscribe to this blog

    Enter your email address:

    Other subscription options

  • Archives