The team reinvented inputs to their models, including using medical data, COVID case counts and macroeconomic data, and shifted from forecasting based on a number with confidence intervals to scenario-based forecasting. The pandemic was the trigger for her team to make changes and implement new ideas. When toilet paper sales surged by 213% at the height of the Covid-19 pandemic, Amazon used AI-driven predictive forecasting to respond quickly to unforeseen demand signals and increase adaptability to market fluctuations Freshwater notes, “Of course, we could have never anticipated that spike prior to COVID, but our models reacted quickly to the new demand trend.”įreshwater recommends that retailers reprioritize their machine learning roadmaps to cope with the unexpected. And when demand spikes unexpectedly, the burden on the supply chain can become even more difficult to handle without modern forecasting methods.
0 kommentar(er)
