Profit From Your Forecasting Software

CHAPTER 7Inventory Control, Aggregation, and Hierarchies

7.1 INTRODUCTION

In many organizations, forecasts guide decisions on how much safety, or buffer, stock to hold to reduce the probability of stock-outs to an acceptable level. The point forecasts we have focused on in the preceding chapters are not sufficient to provide this guidance – we also need to know how much uncertainty surrounds the point forecasts. For example, if we have a point forecast for next month's sales of 200 units, the actual sales might turn out to be anywhere between 80 and 320 units, so we need to take this into account when deciding on our inventory levels. In this chapter, we will look at how computer software estimates uncertainty and how this can be used in inventory planning.

It is important to distinguish between a demand forecast and an inventory decision. A demand forecast is an estimate of what is likely to happen to sales in a future period. An inventory decision is a manager's choice of how much stock should be held in light of the forecast. For example, the forecast might indicate that the most likely level of sales next month is 300 units. However, to cope with the possibility of higher demand than this, we may decide to have 360 units in stock at the start of the month. If we call the latter figure a forecast, then other managers might mistakenly think that 360 units is the most likely level of sales and make their decisions on this basis. In addition, our forecast accuracy is likely ...