Forecasting is the estimation of the value of a variable (or set of variables) at some point in time in the future. Typically, the purpose of predictive calculations in an enterprise is to provide information to the planning process. Forecasting proceeds from the assumption that if a company can at least approximately predict the future, then it will be able to choose its optimal behavior (Kolassa & Siemsen, 2016). Thus, when the future comes, it will be in a better position. The primary purpose of demand forecasting systems is to optimize the supply of goods to stores.
The forecasting systems indicates how much of a given product will be sold in this store during the time between deliveries. If a company knows what demand there will be for a product, then the optimal order size can be easily calculated based on the product’s stock and a given level of minimum stock. Despite this seeming simplicity, consumer demand is subject to constant fluctuations and depends on dozens of factors, from price levels to weather. Errors in forecasts threaten overstocking of warehouses, decreased turnover, and write-offs after the expiration date of goods. They can also cause a shortage of goods, but in any case, this will lead to lost profits. Despite the usefulness of demand forecasting systems, experience with them has not always been successful. A classic example of this is the case of Nike in 2001.
The managers of a large sportswear and footwear manufacturer decided to implement the IT tools for demand prediction and supply chains from i2 Technologies. The company spent about $400 million on this project. After nine months, managers admitted that the forecast for some products was overstated so that they had to be sold at a discount of more than 50% (Bowles, 2020). The other part of the assortment, on the contrary, was immediately sold out, and urgently ordered additional lots had to be transported by plane, which increased transport costs 12 times. The publicity of this fact provoked a collapse of Nike shares on the stock exchange. In this situation, i2 Technologies representatives’ statement that the reason for the false forecast was not a “bad system,” but its incomplete “customization” and deviation from the recommended implementation methodology, did not look comforting either. Thus, forecasting can positively impact the company’s performance, but sometimes it can lead to significant problems.
References
Bowles, R. (2020). Demand forecasting & demand planning for higher retail profit margins. Logiwa. Web.
Kolassa, S., & Siemsen, E. (2016). Demand forecasting for managers. Business Expert Press.