By Stephanie Augier, International Analytics Product Director, IRI
As FMCG manufacturers and retailers continue to adapt to new shopper behaviour in response to the COVID crisis and understand the impact on categories and channels, demand forecasting has never been more relevant or timely than it is now to help track changing consumer demand. Here are my six rules of demand forecasting within the context of the current global pandemic.
- Forecasting regularly
Forecasting tends to be looked at once a year when there’s a planning review, but now more than ever it must be done regularly to help identify change and enable a business to plan accordingly. In the current crisis, this allows clients to create different scenarios, and understand the impact of second lockdowns and new restrictions. The rule of thumb is the more often you do it, the better.
- Planning for the unexpected
COVID is certainly the biggest challenge that manufacturing and retail client are facing right now, but it’s not the only one. Forecasting methodologies can be used to handle different cases, and help in any sort of scenario, such as planning for regulatory changes in the industry.
- Prioritising the short-term
Long-term forecasting is the norm for fast moving consumer goods (FMCG) retailers and manufacturers, but what this pandemic has taught us is that we need to look at the short-term as well. A view of changing consumer behaviour and demand week-by-week can highlight what is happening today in a particular region, but also within the context of the business.
- Invest or stagnate
We tend to assume that all organisations run forecasting studies, but often it comes last on the list of priorities. Often regarded as less important than other forms of measurement, many companies are not prepared to invest in it or measure the ROI of forecasting in the same rigorous way they do for marketing mix activities. In fact, forecasting should sit at the heart of any business, where even 1% of accuracy can make a huge difference to the bottom line.
- One size does not fit all
Forecasting is not a one-size-fits-all approach. It must be relevant and specific to the business, down to the category, product and geography. There could be thousands of metrics that apply to a company, as well as market variables like online vs. offline, and market specific or seasonal trends. Forecasting algorithms can help figure out which are the right ones at the right time.
- Technology evolution
Technology behind forecasting continues to advance with machine learning, artificial intelligence (AI) and simulation, providing even greater accuracy and speed at a critical time. Internet on things (IoT) sensors and analytics also allow FMCG businesses to better track the movement of products through the supply chain, giving them a more accurate source of data for their modelling. But while machines and technology get smarter, let’s not forget the all-important human element that can never be replaced.
In uncertain times, with consumer demand constantly shifting and unpredictability the new normal, forecasting remains more relevant now for FMCG and retail organisations to stay ahead of the game and overcome or limit the impact of this and any future crisis.
Scenario Testing for a second wave in Autumn
Frozen Vegetables case study - Greece

Source: IRI Analytics Center of Excellence – Greece Frozen Vegetables forecasting model