Maybe you are doing your demand forecasting completely wrong. To be more precise, there are two equally important outputs of demand forecasting and you may be focusing nearly all your energy on only one, and maybe even the wrong one. And the impact is that you may not be getting the forecast accuracy you want. Or even more important, that you may not be getting the service levels and inventory efficiencies that you need. And if that's true, you are not alone.
I know for sure that human behavior could be predicted with data science and machine learning. Taking a look at human behavior from a sales data analysis perspective, we can get more valuable insights than from social surveys. In this article, I want to show how machine learning approaches can help with customer demand forecasting. Since I have experience in building forecasting models for retail field products, I'll use a retail business as an example. Moreover, considering uncertainties related to the COVID-19 pandemic, I'll also describe how to enhance forecasting accuracy.
We're excited to announce that you can now measure the accuracy of your forecasting model to optimize the trade-offs between under-forecasting and over-forecasting costs, giving you flexibility in experimentation. Costs associated with under-forecasting and over-forecasting differ. Generally, over-forecasting leads to high inventory carrying costs and waste, whereas under-forecasting leads to stock-outs, unmet demand, and missed revenue opportunities. Amazon Forecast allows you to optimize these costs for your business objective by providing an average forecast as well as a distribution of forecasts that captures variability of demand from a minimum to maximum value. With this launch, Forecast now provides accuracy metrics for multiple distribution points when training a model, allowing you to quickly optimize for under-forecasting and over-forecasting without the need to manually calculate metrics.