Forecasting Inaccuracy & Accuracy

Reasons for forecasting Inaccuracy
Lack of participation by functional managers in the development of & the execution of a forecast system.Forecast requires alignment with one another to ve effective.
Too difficult to understand. If a forecasting tool is too difficult to understand it will most likely fail.
The more complex is the forecasting tool, the more isolated users are from the process& the more work is required to maintain it. Such a tool is also likely to be more costly to run & maintain.
Lack of compatibility bet’n the forecasting system & the capabilities of the organisation. If the techniques are not understood & the results are not trusted, managers are unlikely to follow the forecast & rely instead on informal techniques or gut feelings.
Data may be inaccurate either by collection errors or classification errors, including errors in sampling methods, data classification, measurement, aggregation, time collection & overlooking important data.
Some data are inappropriate for forecasting. Some items should not be forecast such as dependent demand or parts within the final assembly schedule.
Lack of monitoring. Some companies do not check the accuracy of the forecast. They do not track actual sales against projected sales & hence have no way of assessing current forecast performance or establishing targets for improvement.

Demand filters
“A standard that is set to monitor sales data for individual items in forecasting models. It is usually set to be tripped when the demand for a period differs from the forecast by more than some number  of mean absolute deviations”. Demand filters are a means of controlling variations by providing a check that limits the amount of the variation from one period to the next. A demand filter typically is a ratio of the new demand to the avg. of the old demand. Stable items should have tight demand filters to maintain more control as significant variations in demand should be examined & explained. Demand filters also prevent order input errors by establishing reasonableness of the order quantities being placed. Any input error will trip the demand filter & hence will be flagged for review & correction.

Improving Forecasting Accuracy
Steps to improve forecast accuracy
Assign responsibility & accountability for forecasts.
Set realistic goals for accuracy.
Tie performance reviews to those goals.
Provide good forecasting goals.
Forecast at the right level of the product structure.
Track forecast accuracy regularly.
Review & improve areas of poor forecast performance.