Demystifying Retail Demand Forecasting post-COVID-19

Three key demand forecasting considerations for a post-COVID world

Shoppers and retailers are all waiting for the world to return to normal. The question is, what will that look like? Right now, it’s pretty clear that retailers will need to evaluate their capabilities when it comes to forecasting and replenishment. The post-COVID world looks to be tough to navigate without the advanced analytical abilities that come with solutions that leverage AI and machine learning technologies. Even before the pandemic, we released a paper that explored the struggle caused by the fact that many retailers are depending on disconnected systems for demand forecasting and are missing the big picture when it comes to a complete view of customer demand. The 2020 Gartner Market Guide for Retail Forecasting and Replenishment Solutions, released just before the pandemic hit the U.S., resonates on calling out some of the key areas that retailers today want to improve their demand forecasting.

“Four benefit areas continue to drive forecasting and replenishment initiatives — revenue lift, reduction in out-of-stocks (OOS), inventory optimization and margin improvement. An analysis of technology provider responses shows improvements averaging 4.7% for sales, 30% for OOS, 21% for inventory and 3% for margin, respectively.”

Gartner Market Guide for Retail Forecasting and Replenishment Solutions

I’m proud that Symphony RetailAI is among the 23 Representative Vendors named in the report. From our experience working with retail supply chain, as well as my own experience, I think there are three primary things for retailers to consider when assessing how to drive these improvements.

Three demand forecasting “must haves” for retailers today

1. One-size-fits-all is out, it’s all about tailoring to fit

Demand forecasting supports and drives the entire retail supply chain and those systems must be designed to help retailers fully understand what their customers want and when. For example, most demand forecasting systems cannot understand the significance of increased demand for fresh produce and how it affects center-store categories, but the impact is significant and ripples across the entire value chain.

For grocery retailers, this is a key aspect of their business and they must be able to depend on their systems for accurate and relevant insights into demand fluctuations and real-time recommendations that optimize availability and serve the customer. This level of data processing can be achieved with AI and machine learning.

“Using AI techniques, different products can be clustered together in an automated and dynamic way to reflect similar and contrasting product behaviors. The product families can change over time to reflect the business changes. Based on such insights, automation can help demand planners address the products in terms of product families, not as singular SKUs that are isolated from each other.”

Gartner Market Guide for Retail Forecasting and Replenishment Solutions

2. The new world of retail requires a new approach to true demand forecasting 

Legacy systems that reply only on historical and sales data and are not designed to fit together to unify the end-to-end supply chain result in gaps that lead to costly errors in the demand forecast. The time has come for retailers to understand that old methodologies are no longer enough to keep up with the demand of today’s consumers. A future-ready system must be scalable and intelligent, providing actionable insights from all data sources – internal  and external  – and be able to perpetually adapt to new market changes, no matter how fast and unexpectedly they occur.

“A linear regression model, with a trend and a seasonal pattern that repeats itself every year, is an example of a typical statistical model. Over time, although the  model may show historical performance, it may not be sophisticated enough to learn to adjust its parameters to be more dynamic and minimize future forecast error to provide a more accurate prediction of the future.”

Gartner Market Guide for Retail Forecasting and Replenishment Solutions

3. Take off the blinders and see the entire landscape

Retailers today must have a holistic view of how all categories respond to one another. The effects of fresh on center store, in-store and eCommerce, varied distribution channels, promotions, stratification – all of these are constantly in flux – now more than ever – and affecting the supply chain.

Even before COVID-19, 52% of retail supply chain executives said they spend too much time data crunching. Demand forecasting systems that include AI and machine learning drive continuous improvement of demand and forecast accuracy. AI can leverage massive sets of information from all directions to help you achieve a true demand picture.

“Supply chain planning leaders should not think of AI in demand planning as an objective, but rather as a tool to reach a business objective.”

Gartner Market Guide for Retail Forecasting and Replenishment Solutions

Are you ready for the demand forecasting challenges ahead?

Retailers must do some soul searching, strategic planning and understand where their growth paths lie post-COVID. From there, they can begin to evaluate how their current forecasting and replenishment solutions are serving them as well as how they can look to update, expand and unify the systems that are essential to meeting their business goals and successfully meeting their customers’ needs.

Learn more: Check out the latest insights around forecasting and replenishment

Gartner “Market Guide for Retail Forecasting and Replenishment Solutions,” Mike Griswold, Alex Pradhan, 28 January 2020.

Gartner does not endorse any vendor, product or service depicted in its research publications, and does not advise technology users to select only those vendors with the highest ratings or other designation. Gartner research publications consist of the opinions of Gartner’s research organization and should not be construed as statements of fact. Gartner disclaims all warranties, express or implied, with respect to this research, including any warranties of merchantability or fitness for a particular purpose.

GARTNER is a registered trademark and service mark of Gartner, Inc. and/or its affiliates in the U.S. and internationally, and is used herein with permission. All rights reserved.


Speak with an expert

Just provide us with a few details and we’ll be in touch to discuss your needs