In most DPL models, decisions are made to maximize or minimize some quantity, and they can and should be left unconstrained. You can never have too much NPV, for example. However, some decision problems require making tradeoffs among several decisions where not all possible decision policies (i.e., combinations of decision alternatives) are feasible. For example, your company may only be able to launch one or two new products a year.
Now that we've had a few days to recuperate and properly reflect, Tony, Chris and I have put our notes together to come up with the top high- and low-lights of INFORMS Annual Meeting 2015:
In just 10 days we’ll be descending upon Philly, the City of Brotherly Love, to exhibit at what will be our 13th consecutive INFORMS Annual Meeting. In keeping with the spirit of the host city's motto, I’m setting forth some ways you can show Syncopation some “conference love” at this year’s INFORMS:
Stop by Booth #1 and say hello
In some sports leagues, particularly those with youth competitors, there is a Mercy Rule by which a game is ended early if one team has built up an insurmountable lead. For example, in little league baseball the rule may be to end the game if one team is ahead 10 runs after 4 or more innings. While the team that's behind may theoretically have a chance, it's much more likely that grinding out the rest of the game would only humiliate the losing team and result in everyone getting home late on a school night.
As I'm sure you've heard, Volkswagen is in a whole lot of hot water after admitting they equipped their diesel cars with software that allowed them to cheat on EPA emissions tests. Affected car models were found to be spewing as much as 35 times the amount of nitrous oxide (NOx) permitted by the EPA in real world driving conditions. NOx is a pollutant that can cause a variety of adverse respiratory problems, particularly in susceptible populations. (https://www.epa.gov/no2-pollution)
Larry Neal's recent column in September's Decision Analysis Today talks about the value proposition of Decision Quality (DQ), and a key point is the Value of Information (VOI). One of the most powerful things about decision analytic methods is the ability to explicitly calculate the value of information, in order to make an intelligent choice about whether to buy it.
Are you building a house, or just pitching a tent?
When you read about decision analysis models in case studies, they're usually described in the narrative as part of an epic process, one that begins with organizational angst and ends with a resounding consensus to pull the lever on that "irrevocable allocation of resources". Right, and sometimes that really happens! But more often, the allocation of those resources is gradual, and even when a single large chunk of capital has been committed, there are steps along the path where the project is reevaluated.
Windows 10 has been officially out for a few weeks now. Most corporate users will be quietly and productively plugging away on Windows 7 for some time, but in the comsumer/student space Windows 10 is replacing Windows 8/8.1, and that is a good thing.
Our take is that Windows 10 is the Oklahoma of operating systems: it is OK. It keeps the good aspects of Windows 8, including clean visuals and touch, while giving desktop users what they expect to do actual work.
July's MOTM is sourced from the Pharmaceutical sector and proves an excellent example of how certain large models, when structured properly, can take advantage of DPL's various compile time optimizations to give you insightful results at exceedingly manageable runtimes.
Model and Results
I was recently at task, testing some keywords (something Marketers do from time to time) and was surprised to see a competitor's webpage description state the following in a Google search result:
"Avoid risk by using Monte Carlo simulation to show possible outcomes in your Microsoft Excel Spreadsheet".
The news of the day is the encyclical on climate change from the Vatican. The document is surprisingly clear and canny; reading it, one can easily forget that it comes not from some management science guru but from the leader of one of the world's great religions.
The subject of Decision Engineering has been gathering increasing attention, most recently with this article in IEEE Roundup.
Among some of my decision, uh, interested friends and colleagues, there's a certain skepticism about new terms that start with the word "decision".
This blog posts describes various steps that may be taken to validate that a DPL/Excel model is computationally correct. The actual testing/validation required will depend on the particulars of your model and the circumstances of the analysis. Accordingly, this is more of a menu one can pick and choose from rather than a checklist. If you use other methods not listed, and they may be generally useful, please add them in the comments section below.
In a recent interview, Reid Hoffman, co-founder and executive chairman of LinkedIn speaks about the nature of data and probability.
"We live in a probabilistic universe, and we tend to think in determinist ways. If A is data-driven and I think I have that data, how certain am I that I have that data? What could I discover that might actually tell me that that data is formulated wrongly? When you dig into it, most of your arguments are actually probabilistic. They're not certain, even when you have data. You're really trying to get a sense of whether you have a reasonable bet on the probability."
For June's DPL MOTM we're highlighting a truly spectacular model from the 90's, the results of which continue to have a significant impact on one of the world's largest and fastest growing economies. The case was submitted by long-time DPL User and prominent scholar in real options valuation, Luiz Brandao, who also holds the title of Professor and Director at PUC-Rio's School of Business.
Larry Neal and Carl Spetzler have a recent article in Harvard Business Review which explains Chevron's multi-decade commitment to Decision Quality (of which Decision Analysis is a key part).
This is a bit like when that alternative band you've been listening to forever ends up playing on Saturday Night Live -- you think "Gee, I thought nobody else knew they were good".