Explainable AI Forecasting

Artificial Intelligence (AI) is not a new concept. In fact, the term was first coined in the 1950s, and universities and data scientists the world over have been studying it ever since. But if you are not a data scientist, then you probably do not have much experience and knowledge into the subject. That is where Explainable AI comes into play. According to Gartner, Explainable AI “enables a better adoption of AI by increasing the transparency and trustworthiness of AI solutions and outcomes.” Ultimately, it refers to the methods in AI technology so that the output can be understood by humans.

AI enabled technology has become quite common in many industries. The grocery and convenience store sectors are no exception. Larger food retailers might have their single day forecast, but many food retailers do not have automated forecasting and conduct manual forecasts based off their experience or gut instincts. As business grows, this only becomes more difficult and more errors in decision making are likely to occur.

While some forecasting engines in use today are reliable and robust, recent technological breakthroughs and competitive data science innovations have challenged us all to dive deeper into data. These advances can be used to enhance business decisions and explore more modern alternatives to traditional forecasting.

For grocery and convenience retailers dealing with fresh products, it is critical to have reliable, understandable data that can be used to make accurate forecasting decisions. It is all about delivering the right amount of product at the right time. Many forecasting systems are ill equipped to deal with fresh by being limited to daily forecasts. The data analysis does not dive deep enough to tackle the challenges faced with intraday shelf lives which can sometimes last only an hour.

Food retailers need help to take the guesswork out of production planning and replenishment. In ADC’s latest FreshIQ® release, we aimed to develop a true Explainable AI forecasting engine for fresh food. One that offers highly advanced time series forecasting capabilities and gives data down to the hour. This more granular data provides real-time visibility into the fresh departments, meaning different items can have different forecasts for production. FreshIQ’s forecasting provides food retailers with the data they need to make the right decisions to increase sales while also increasing gross margins and reducing waste.

ADC’s FreshIQ makes AI explainable by:

  • Creating forecasts and tracking progress toward specific business goals and KPIs (i.e. Forecasts for production planning down to the hour).
  • Understanding and easily explaining the factors salient to those forecasts.
  • Building dashboards that provide insight for faster decision making (i.e. Identify which fresh SKUs perform the best).
  • Incorporating client-specific events and factors to truly fit into client’s business (i.e. holidays, promotional events, etc.)
  • Plus, more…

At ADC, we understand how important it is to have reliable, understandable data that can be used to make production planning and forecasting more accurate. Request a demo and learn more about our Explainable AI Forecasting today.

About the Author


Michael N. Colella is the Chief Data Scientist at ADC where he is responsible for providing the data science perspective on everything we do and infusing our solutions with Artificial Intelligence. Prior to joining the ADC team, Michael was a Director of Data Science at dunnhumby, a global leader in customer-centric retail analytics. At dunnhumby, Michael was responsible for leading analysis for some of the biggest names in global retail, focusing on innovative initiatives. Before his time at dunnhumby, Michael was a Senior Manager of Advanced Analytics at Kraft Heinz where he led the global advanced analytics innovation hub under the CIO. Michael has worked/consulted for various other retailers & Consumer Product Goods companies, including Bayer Consumer Care as well as Wilton Brands, to name a few. Michael has 10 years of experience working on innovative analytic projects spanning Supply Chain Planning & Optimization, FMCG, Big Data, predictive and prescriptive analytics as well as behavioral and cognitive neuroscience.