Backtesting

One of those cognitive dissonances that, for now, has passed into embarrassed history, but is sure to re-emerge the moment the financial market returns to giddy optimism that characterizes large epochs of its history.

Back in the day, a resourceful salesperson with a clever new product (involving leveraged alpha, for example) had to go through the motions of justifying its extraordinary potential when pitching it to their marks.

The problem with financial markets was, is, and always will be this: you can’t anticipate the future. This isn’t a shortcoming of contemporary financial management techniques, by the way: it’s in amarket’s very nature. If you could, you couldn’t make money betting on it.

So these randy salespeople needed something their clients could take back to their risk committees to demonstrate the rigorous financial analysis that had gone into the product design. The lightbulb moment was the invention of backtesting. There may be a total lack of data from the future, but there’s any amount of it from the past. Your Bloomberg terminal is your friend. One could compare how the strategy would have done had it been running in, say, the five years leading up to the present. A crafty salesperson would extend the backtesting period over a known period of market shock, to illustrate how the strategy would have performed.

Thanks to the “chart” function in Microsoft Excel could render these illustrations in multicoloured, three-dimensional boxes, graphs, Gantt charts and fishbone analyses. It was brilliant. In every case the strategy outperformed beta and any other indicator in the market that the salesperson cared to represent. But the restaurant booking was in twenty minutes, so the client had seen all he needed to see.

See also

• Confirmation bias
• Snake-oil