Hitchhiker’s Guide to Analytics — Bistromathics

The numbers are awful

Greg Anderson
Creative Analytics
Published in
5 min readOct 16, 2020

--

The Hitchhiker’s Guide to the Galaxy describes a number of awe-inspiring methods of traveling the incredible distances involved in traipsing across the galactic disc without expending three or four generations of your family.

Teleportation. Time travel. The Infinite Improbability Drive, which powers the truly amazing Heart of Gold and allows near-instantaneous travel to any point in the galaxy while avoiding the dangers and complexities of hyperspace.

Bistromathics

The starship Bistromath is not impressive on first sight. Or second sight. It loses some of its charm on third sight and trails off a bit from there.

The way it moves, however, makes the Heart of Gold seem like an electric pram.

Welcome to the future

Light, which travels so quickly that it takes most civilizations centuries to realize it travels at all, take over 100,000 years to cross from one side of the Milky Way to the other.

This ship can cover two thirds of that distance in less than a second.

From the Guide proper:

The Bistromathic Drive is a wonderful new method of crossing vast interstellar distances without all that dangerous mucking about with improbability factors.

Bistromathics itself is a revolutionary new way of understanding the behavior of numbers. Just as Einstein observed that space was not an absolute but depended on the observer’s movement in space, and that time was not an absolute but depended on the observer’s movement in time, so it is now realized that numbers are not absolute but depend on the observer’s movement in restaurants.

Admit it. You’re not totally surprised, just a little worried.

How It Works

Bistromathics works by exploiting the uncertain nature of three numbers.

The first non-absolute number is the number of people for whom the table is reserved. This will vary during the course of the first three telephone calls to the restaurant and bear no relation to the number of people who actually turn up.

The second non-absolute number is the given time of arrival, which is now known to be one of those most bizarre of mathematical concepts, a recipriversexcluson, a number whose existence can only be defined as being anything other than itself.

The third and most mysterious factor lies in the relationship between the number of items on the check, the cost of each item, the number of people at the table, and what they are each prepared to pay for.

The uncertain nature of these numbers is not actually surprising in any way. We just never thought about using them to power interstellar travel.

Deep in the fundamental heart and mind of the universe, there is a reason.

Bistromathics in Analytics

Bistromathics, as a science, has a few things in common with analytics today.

The first and most compelling similarity was stated best by Slartibartfast, when he was attempting to describe the engine to Ford and Arthur.

“The numbers are awful.”

The second and (maybe) more relevant factor is the uncertainty. Or, if we’re being precise, the acceptance of uncertainty.

Really?

Yes, really.

Look at the three pillars of bistromathics, which we’re going to pretend is a real science. There is no need to explore them in depth; if you’ve ever been to a restaurant, you know exactly what Douglas Adams was saying.

I can draw hard analogies from the three tenets of bistromathics to project management.

  1. You’ll never have the number of people or amount of time agreed for your project. Priorities change. People leave. Some just won’t like you.
  2. Projects are almost never completed at the date and time initially planned. They can be early, late, or canceled, but rarely on time.
  3. People fight over money. Corporate teams fight over money.

…But that’s boring. If you’ve ever worked in a restaurant that takes reservations or just manages its seating, then you probably had to stop reading and take a deep breath.

You might want to exhale now, by the way.

None of those three factors should be uncontrollable, yet most groups will completely fail to control them. Some won’t even try.

The bit about splitting the check? That’s usually just someone in the party being cheap (or exercising some even less desirable personality trait).

Making It Work

You’ll never get anywhere in hospitality or analytics (or bistromathics) if you cannot manage some level of uncertainty.

I should note (before someone interjects) that space travel requires, in fact, a great deal of precision and allows very little room for uncertainty.

Point being, outside of air and space travel, you can either insist on getting it 100% right or you can actually complete your project. Accept the uncertainty.

Embrace the uncertainty. Maybe take it to dinner. Have some wine.

In fact, you have to accept the uncertainty in order to address it. Trying to deny its impact will not only impede your work but also make you look foolish in the process.

I particularly love the idea of the recipriversexcluson, a number that can only be defined as having a value that can be anything other than itself. Any analyst that claims to have never encountered such a number is either inexperienced or lying.

In Conclusion

Of course, the starship Bistromath would likely never fly. First, it’s fictional. Second, Slartibartfast admitted that he did not understand how it worked. That uncertainty actually provided the motive power to cross the galaxy.

It didn’t matter whether his understanding of bistromathics was perfect (or even accurate). It mattered that the ship flew safely and got them where they needed to go.

You can still produce useful results as long as you admit the uncertainty in the model and the analysis. Or, more likely, in both.

Accept that sometimes, the numbers are awful.

--

--

Greg Anderson
Creative Analytics

Founder of Alias Analytics. New perspectives on Analytics and Business Intelligence.