FMCG retailers today are hyper-focused on being able to prepare for and respond to sudden and significant changes in demand and buyer behavior. One of the key lessons learned during the COVID-19 surge in the 2nd half of 2020 is that traditional demand forecasting methods are no longer enough.
The key is putting a system in place that enables retailers to react to massive disruptions in the supply chain while, and after, they are happening and make that system sustainable moving forward. To do this, full inventory visibility is a must.
This will be the topic of the fourth part of my series on the key questions you need to consider about your demand forecasting solution.
The Question: Are you able to react quickly enough, daily or even intra-daily, and generate accurate forecasts to meet changing shopper needs?
Focus on inventory visibility is not new – but it’s become an essential priority
A research survey conducted in December 2019 revealed that 76% of retailers named real-time inventory visibility as a key focus area for improvement in the supply chain. Further, 70% of retailers named the ability to respond more rapidly to demand a “very important” driver of supply chain strategy. In the wake of the events of the last year, these issues have only come into sharper focus.
Shopper behavior has dramatically changed and continues to change as we all manage the impacts of the events of 2020. Cross-channel demand and fluctuating purchasing frequency have a high impact on retailers’ ability to forecast what needs to be available and when and how it will be fulfilled. The demand for fresh, prepared and foods-to-go remain high but are more subject to cross-channel demand than before. Retailers that serve prepared foods must have data insight to guide forecasting and replenishment decisions that meet the demands of shoppers as well as an understanding of how all the categories are affecting each other.
Moving forward, the vital component for every retailer’s supply chain is full and accurate visibility into their inventory. Considering true inventory availability across the supply chain when responding to forecasted quantities gives you the ability to not only confidently predict changes in demand but the agility to respond rapidly when they hit unexpectedly. Further, it enables you to support complex logistics networks, sourcing and pulling product from multiple locations and/or vendors during a period of disruption.
The Solution
Demand forecasting systems that include AI and machine learning drive continuous improvement of demand and forecast accuracy. Algorithms are continuously retrained using historical, current and contextual data without requiring user intervention.
Further, the AI will be able to fully understand the event as an anomaly that would not normally exist in the demand cycle. It will be able to incorporate historical data pre-event, data during the event and the incoming data post-event. This results in a full understanding of the impacts of the disruption on shopper behavior in the near and short term.
AI-enabled systems also remove the need for manual data manipulation and can process all the disparate data sources in seconds to deliver actionable insights to the entire enterprise on any device. This enables buyers, analysts and demand planners to spend less time chasing data and reports and more time on critical tasks.
Read more about the research mentioned in this post in the RSR Research Benchmark Report, The Retail Supply Chain: Designing New Ways To Satisfy Demand
Learn more about SymphonyAI’s solutions and insights for inventory management, mobile store operations and assessing demand across all categories from fresh to center store.
Read part 1 of the series: Is your demand forecasting solution working for you or are you working for it?
Read part 2 in the series: Are your demand forecasting systems connecting all categories across the store?
Read part 3 in the series: Why demand forecasting must be effective with all channels to be effective with any
Read part 5 of the series: Don’t let your demand forecasting depend on history to repeat itself
