Forecasting Daily Demand in Cash Supply Chains
Read this article. It is important because seasonal demand is addressed as the authors attempt to successfully predict demand. In your experience, what are some seasonal products or services that you purchase?
CONCLUSION
Results confirm the potential of advanced forecasting techniques for cash supply chains and help explain variability in daily cash demand. Reduced forecasting errors result in lower demand uncertainty and enable supply chain partners to coordinate replenishments across the cash supply chain. However, the potential for information sharing seems to be limited to this role and does not necessarily translate into more accurate forecasts based on joint forecasting.
Limitations of this study arise from the simple two-stage supply chain framework and the relatively small amount of data available. Long-run time series contain more observations of calendar effects such as holidays and may provide further insights. In addition, cumulative forecasts are very robust, since forecasting errors are offset over a period of 14 days. Similar effects may explain, why the joint forecasting model does not yield substantially better forecasts. In fact, anomalies in one series may be passed on to all other series increasing forecasting errors system-wide. However, limitations linked to the applied error measure, the mean absolute percentage error, can be regarded minimal given the nature of the data.
Results of this study provide preliminary evidence and call for further investigation of joint forecasting in a multi-stage supply chain spanning more than two stages. Further research will have to address additional exogenous variables such as weather and festivals that may dominate certain calendar effects. Advanced forecasting models may additionally provide the link to scenarios and risk models in cash supply chain management.