Handicap Triage And Fast-And-Frugal Trees (FFTs)

In Learning from small samples: An analysis of simple decision heuristics, the authors recount how, in 2009, two experienced pilots decided their course of action after '...a commercial passenger plane struck a flock of geese within two minutes of taking off from LaGuardia Airport. The plane immediately and completely lost thrust from both engines, leaving the crew facing a number of critical decisions, one of which was whether they could safely return to LaGuardia. The answer depended on many factors, including the weight, velocity, and altitude of the aircraft, as well as wind speed and direction. None of these factors, however, are directly involved in how pilots make such decisions. As copilot Jeffrey Skiles discussed in a later interview, pilots instead use a single piece of visual information: whether the desired destination is staying stationary in the windshield. If the destination is rising or descending, the plane will undershoot or overshoot the destination, respectively. Using this visual cue, the flight crew concluded that LaGuardia was out of reach, deciding instead to land on the Hudson River. Skiles reported that subsequent simulation experiments consistently showed that the plane would indeed have crashed before reaching the airport...'

Fast-And-Frugal Trees (FFTs) are the ultimate expression of heuristics and have been successfully applied to medical situations - most notably heart disease triage in emergency rooms.

Though obviously worlds apart from life-or-death, medical-triage emergencies, sports handicapping lends itself quite well to the use of heuristics (FFTs) as a shortcut alternative to currently popular, elaborate machine-learning approaches! Perhaps it is the engineer's defeasible reasoning that attracts us to these simpler, more elegant, and more easily explained techniques. With respect to horse-racing, there is a strong emphasis placed on a horse's past performances as the most likely indicator of future performance. Such an emphasis has a certain logical appeal on the surface. However, at a deeper level (see accompanying graph - percentages for illustrative purposes only), the key determinant of a horse's performance today is the current form of the stable (i.e. trainer). This scenario was clearly illustrated over the weekend when a graded stakes race was won by a horse (eight of ten in the betting order) from a stable the runners from which are currently beating 62% of their respective opponents against a market expectation of 45% (see WASP Trainers)! In other words, the simple factor (attribute, cue) of trainer form was probably the defining heuristic in deciding the outcome of that graded stakes race.