Our focus in this blog series has been to establish forecast accuracy targets. In very general terms, the goal should be to add value to the business through the forecasting process. We have however focused on the forecast value add and using that to create a minimum acceptable forecast accuracy target in the previous blog. Now we will take that a step further and talk of ways of improving it.
It is important to measure and improve the forecast accuracy at the right level of aggregation. If you measure at too high a level, your accuracy picture will look better than what it needs to be as the data at high (aggregated) levels is more forecastable. By contrast, at too low a level...
A successful demand planning process accurately forecasts demand and revenue streams, and subsequently drives the next steps in the S&OP process which are Inventory, Supply Planning, and Optimization. Therefore, it is a crucial step in an organization's S&OP process.
A company’s total inventory is built up of many different parts such as strategic stock, anticipation stock, safety stock, cycle stock, unplanned stock. The cycle stock is the one most connected to the demand forecast; it is expected to be sold as the forecast becomes real demand. Safety stock on the other hand is extra stock to deal with the variability of the demand or supply. As such, it is not always linked to forecasting accuracy.
Learn the best approach to setting forecast accuracy targets and how to set expectations for your management team.
Having access to an accurate forecast is very beneficial for businesses. If used correctly, it can provide better margins, increase market shares, and many other positive results. At a more tactical level, it can help reduce the costs associated with meeting the customer demand and make the supply chain more efficient.
In a previous blog post, we discussed how a high or low value of Coefficient of Variation (CV) impacts the first or second term of safety stock. Today we decided to put this to the test using real customer data - here we will discuss our findings.
In this blog we briefly cover some key insights for successful time series forecasting: (a) Profiling the Shape of the Curve is the first stage, and the first step is assessing if the time series is stationary. (b) The forecast method identified must capture the shape and be able to project the shape across time. (c) There are limits in historical and no amount of “fancy math” can overcome them.
Some time ago, I had been trying to help a business improve its statistical forecasting. We tried different parameters and different forecasting algorithms but the statistical forecast for about half of the products could not be improved no matter what we tried. We decided to do a deep dive to understand the reason.
In this blog, we will illustrate through an example of these potential pitfalls (unanchored, random variation, and narrow metrics) and potential negative impact on a firm.