Statistical Sales Forecasting?
A library of statistical sales forecasting algorithms is often the main assistance provided by many sales forecasting software solutions.
Prophecy naturally has its own statistical forecasting engine. However, it is important to assess statistical forecasting's relevance to your forecasts before relying heavily on the sales forecasts any statistical engine generates.
Is Statistical Sales Forecasting the Right Solution?
- Statistical forecasts are slow to react to changing environments
- It is hard to build in 'soft' information to statistical forecasts
- Statistical forecasting requires an unreasonable level of statistical and mathematical understanding from business forecasters, or a "black box" trust in the maths.
- If you don't know why the statistical algorithm has forecasted a peak or trough, how can you sensibly override it?
- Marketing = "Never the same thing twice". How can statistical forecasting understand that?
- Purchasing behaviour is behavioural, not mechanistic.
- Sales are often a complex function of a large number and variety of causal factors.
- Causal factors are difficult to consistently quantify (or even identify, in some cases).
So, there are numbers.... and there are forecasts!
- How much of the forecasting process involves reviewing existing forecasts in the light of the latest actuals and known future event changes, compared to originating a completely new forecast e.g. to initialise a new year?
- How much does another month of actuals as input to a statistical forecast improve its accuracy anyway?
- Does greater mathematical complexity equate to more accurate statistical forecasts? (Our tests suggest probably not.)
- How do you ‘clean up your data’ for statistical forecasting (without excessive use of judgement)?
- What is the magnitude of the trend (which statistics may be good at forecasting) versus the magnitude of events, such as promotions, competitor activity etc. on the short and medium term sale?
- Purchasing behaviour is behavioural, not mechanistic. By this, we mean that sales may respond differently to the same causal factor. For example, where the buyer was overstocked last time they may order low this time.
- How accurate, and at what time, product and customer granularity, do the forecasts have to be? If you've tested the statistical algorithms and you find they are accurate enough.... then great! But our experience suggests they are unlikely to be accurate enough in most real-world markets.
So, is there a solution?
Nobody said sales forecasting for business was easy!
However, it is important to accept that statistical forecasting has major limitations for real world sales forecasting. Whilst alternative approaches require more time investment, the results are likely to be significantly better. Consider the following alternatives to running and re-running statistical forecasting algorithms:
- Use the 80:20 (Pareto) rule or other types of product / customer classifications to focus time and attention on the relatively small number of skus or customers that account for a relatively high proportion of sales. If you have not already run an 80:20 analysis on your skus you may be surprised how few account for so much of your business. (Tip: Prophecy™ can be configured to provide instant Pareto views for any selection of products or customers.)
- Forecast the 80% of skus that typically account for the smallest 20% of sales less frequently or by exception. For example, after next year has been forecasted only revisit the forecast for known significant events or by exception as the year begins to sell. Prophecy's built in accuracy analysis, trend graphs and Advisor text will help your forecasters quickly identify when these exceptions occur.
- For the 80% of skus that typically account for the smallest 20% of sales, consider whether it is more efficient to let the statistical algorithm generate a forecast and then spend time correcting it, or use one of Prophecy's easy data-entry features to eyeball the sales line and spread / pro-rate a total annual forecast across the year. (Hint: maybe it's the latter!)
- Remember that a majority of business forecasting activity involves reviewing your existing forecasts in the light of the latest information, rather than generating completely new forecasts. Another month of history is unlikely to help a statistical algorithm improve the current forecast, whereas applying human judgement to the latest information about the marketplace, buyers, stocks in the trade, promotions, competitor activity etc. really can improve accuracy. Use a tool like Prophecy™ to help forecasters flex their forecasts in the light of these ever-changing factors.
- Review the existing forecasts with a "can I defend this number?" mindset. In other words, look at moving annual totals, percentages versus previous years, the sizes of forecasted peaks and troughs versus previous years. Keep objectively challenging the forecasts until growth rates and peaks/troughs look 'reasonable'. Although it takes time, Prophecy™ can greatly speed the process up for you. The ROI, in terms of the financial benefits of improved forecast accuracy, makes it time very well spent.
Further considerations - the 'soft' benefits
Do not overlook the 'soft' benefits of making human forecasting the core of your forecasting process:
- Individuals become responsible for turning their forecasts into reality.
- The discipline of forecasting helps forecasters really understand the dynamics of their markets.
- The forecast review / S&OP process generates collective 'buy-in' to the forecast and to the business plan.
- Everyone in the organisation is 'singing from the same hymn sheet' and therefore working in a coordinated way towards delivery.
Evaluate Prophecy™ for your sales forecasters. It was built from the ground upwards to address the limitations of statistical forecasting in the real world.
Contact Data Perceptions to discuss how Prophecy could help your sales forecasting processes.