Let’s face it: most sales forecasting is a complete joke. Here’s the routine:
- The sales manager asks for the forecast.
- The reps make a guess at what will close, then subtract ten percent, just in case.
- The sales manager takes the forecast and raises it ten percent because he knows the reps are fudging.
- The sales manager gives the forecast to top management.
- Top management changes the numbers to match analyst expectations.
- Manufacturing ignores the numbers and orders raw materials based on last year’s actual sales.
- Actual sales, when they happen, turn out to bear no resemblance to any of the above.
- Prior to earnings announcements, accountants jigger the books so that they resemble the forecast.
Sound familiar? Worst case, the above scenario ends with a debacle like Worldcom. Best case, forecasting is a waste of energy and effort. And that’s too bad, because if most companies had a truly accurate forecast, they’d be more profitable and better able to attract long term investors who love predictability.
The irony of the situation is that any company can have an accurate forecasting system. Here’s how:
- Hire a mathematician to build a computerized forecasting model that predicts future buying behavior based upon previous years’ sales, seasonal changes in buying patterns, historical impact of marketing campaigns, overall state of the economy, fluctuations in currency exchange rates, and so forth.
- Test the model against historical data to confirm that if it had been in place in the past it would have accurately predicted sales.
- Goal sales and marketing on providing information that hones the accuracy of the model. For example, suppose the sales rep for a shoe wholesaler comes back from a meeting with a major retailer, where the retailer noted that low-income consumers were purchasing more shoes made from genuine leather. That bit of information, when fed into forecasting model, would signal to manufacturing that they’d better switch materials.
Over time, the model becomes increasingly accurate. While it will never become 100 percent perfect, it’s far more likely to reflect reality than the helterskelter system that’s in place in most firms today.
Sound like science fiction? Maybe so, but Dr. John Mentzer, a professor at the University of Tennessee who’s spent thirty years studying forecasting, can point to many examples where scientific forecasting has worked in real-life situations. For example, when Brake Parts, Inc., a division of Dana Corporation, implemented scientific forecasting in the mid-1990s, it immediately saved $6 million in excess inventory.
Unfortunately, scientific forecasting of the Mentzer variety will remain a curiosity rather than business as usual, and the insanity that is forecasting will remain exactly as insane as it’s always been. I’ll explain why in my next post.
Meanwhile, feel free to share your forecasting stories. Is your process as broken as the one I described at the beginning of the article? I’ll bet that there’s not a single person out there whose company has bit the bullet and actually hired a mathematician.
