Bombers with bullet holes
During the dark days of World War II the American military presented their Statistical Research Group with a problem. They wanted to add additional armour to their bombers, but clearly couldn’t put the armour everywhere because of the additional weight it would add to the planes. The group was tasked with working out how much armour to allocate to the various regions of the aircraft to maximise defence whilst minimising any effect on fuel consumption and agility.
Engineers inspected a number of bombers that had seen some action. These planes had bullet holes that were distributed mainly across the wings and body. Comparatively the engines and cockpit had much less damage. This had lead the commanders to make the obvious, but foolish, conclusion that they should enhance armour on areas that had been hit most frequently, namely the fuselage and wings.
One of the many geniuses of the group, Abraham Wald, realised that they were looking at the problem from completely the wrong angle. It’s not that planes weren’t being hit as frequently on the engines and cockpit, but rather those that had been never returned to tell the tale! These were the parts of the aeroplane that needed enhancement, not the areas that could take a battering and still survive.
Survivorship bias
Countless articles, books and documentaries have been produced about successful people and how to capture the principles of their success to improve your own fortune.
Consider Steve Jobs — frequently heralded as a one of the greatest geniuses of our time — how do we emulate his success? Clearly dropping out of college, spending time at meditation retreats and starting a business from your parent’s garage is the way to go. But what about the hundreds of thousands of budding Apple founders for whom this strategy never quite worked out?
Books aren’t usually written about failed enterprises, just the rare, billion-dollar, success stories.
Choosing tech thoughtfully
As well as being responsible for the latest diet fads and the exaggerated performance of mutual funds, we can see this bias lurking in certain corners of the software development world.
How often do you see a wave of enthusiasm for the next high throughput NoSQL system or a push for complicated elastic scaling technology? Companies such as Twitter and Netflix present their wild successes but we don’t usually see qualifications on the size and scale of the teams implementing these solutions.
It’s worth keeping in mind the potential for a mass of silent teams. Struggling under the weight of overpowered, over-engineered, “web-scale” technologies inspired by the industry front-runners. Most of us mere mortals just don’t have the resources, skills, or (most importantly) even the need for such high class deployments. Most of the time it’s just better to keep things simple and known.
Similarly, businesses push on with “AI” for fear of missing out, but without any real understanding of what they really need. Solutions are commissioned that aspire to the heights of Facebook and Google whilst in reality they fumble for a real business-value providing use-case.
Don’t get me wrong, I’m 100% all for learning new paradigms, languages and frameworks. This is just a reminder, as much to myself as anyone else, to take a moment to think past the biases that may lead us to make some regrettable, albeit well-intentioned and over-excited, choices.
Top comments (1)
Yep! It's really, really, important to learn from others' mistakes and failures. One of the many reasons why I am a big history buff is that, well, I want to learn about the mistakes done by past civilizations. After all, things in the past and in today are not so different.