Ineffective forecasting of grocery demand contributes to a higher level of waste than one might anticipate. In the United States, grocery stores discard approximately 10% of the roughly 44 billion pounds of food produced annually, as reported by a reliable source. This not only has negative environmental implications, as food waste is a significant contributor to carbon emissions, but it also imposes financial burdens on grocers. According to Retail Insights, insufficient inventory availability leads to a loss of up to 8% of revenues for food and grocery retailers.
Entrepreneurs Euro Wang and Jack Solomon personally encountered the micro-level consequences of the forecasting issue at their neighborhood supermarket, where their favorite guacamole frequently went out of stock.
“It turns out that even the largest retailers struggle to predict future demand and frequently overstock and understock inventory,” Wang explained in an email interview. “With more extreme weather in recent years, there’s increasingly been supply shortages in fresh food. That makes the efficient allocation of the limited supply all the more important. On top of this, inflationary pressures and increases in labor costs have been threatening grocers’ margins more and more.”
Motivated to address the issue with technology, Wang and Solomon joined forces to establish Guac, a platform employing AI to forecast daily sales for individual items at specific store locations. In a recent seed round, Guac secured $2.3 million in funding, with 1984 Ventures leading the investment and support from Y Combinator and Collaborative Fund.
“Food waste and food security are issues that Jack and I care deeply about, and we were really excited about an opportunity to actually address food waste at its core,” Wang said.
Before founding Guac, Wang was employed at Boston Consulting Group, and Solomon conducted research in AI for grocery logistics. Their paths crossed during their undergraduate studies at Oxford University, where they first met.
At Guac, Wang, Solomon, and the dedicated engineers collaborate to construct customized algorithms. These algorithms anticipate optimal order quantities for grocery items by considering variables like weather conditions, sporting events, betting odds, and even analyzing Spotify listening data to grasp consumer purchasing behavior. Clients of Guac receive personalized recommendations, encompassing details such as shelf life, minimum order quantities, promotions, and supplier lead times. These insights seamlessly integrate into their existing inventory ordering software and workflows.
“Traditionally, forecasting is done using Excel formulas or simple regression models,” Wang said. “But for fresh food that expires quickly, you need something better … Because we use so many external variables, we’re able to identify which real-world variables cause the changes in demand.”
In the realm of food demand forecasting, Guac is not the sole player. Crisp offers an open data platform covering every aspect of the grocery supply chain, while Freshflow is developing an AI-powered forecasting tool aimed at assisting retailers in optimizing the replenishment of fresh and perishable goods in their stock.
However, according to Wang, Guac stands out due to its commitment to transparency and the meticulous refinement of its forecasting models.
“Our machine learning model isn’t like a black box that mysteriously predicts a 20% increase in demand — instead, we tell our customers things like, ‘This 20% increase is because there’s a conference happening nearby,’” Wang said. “Even if a retailer is already using machine learning, we can still improve their forecasting because of our access to a lot more external datasets. When we remove our unique external variables that we use and only include the basic datasets (e.g. weather and public holidays), we actually see the forecast error double.”
Some early customers are convinced that Guac can add value. The company is working with retailers, including grocery delivery companies in North America, Europe, and the Middle East, and has partnered with an unnamed supermarket chain with around 300 locations. Guac is also already generating revenue and anticipates being able to expand its engineering team in the coming year.
“The grocery industry is fairly resistant to economic downturns,” Wang said. “Everyone has to eat, and when the economy slows down, people are actually buying more groceries because they eat out less. And the pandemic helped speed up digitization in grocery stores, which allowed us to integrate our predictions with customers’ systems more smoothly. On the subject of the pandemic, shoppers behaved very differently during the pandemic — which means it’s a lot harder for grocers to just rely on the past three years of historical sales data to predict future demand. With our algorithm, we’re able to adjust for the ways the pandemic biased sales data in 2020 and 2021 — and even for the residual effects of the pandemic afterwards.”