Distilling Supply Chain Success with AI Forecasting

Southern Glazer’s Wine & Spirits is the US’ largest wine and spirits distributor, orchestrating a supply chain operation that’s as considered as it is colossal. 

The beverage company’s story begins in 1909 with something simple; flavoured soda water delivered on horse-drawn wagons. Fast forward more than a century and Southern Glazer’s now covers 47 US markets and stretches beyond into Canada, the Caribbean and South America. 

That scale is the result of smart planning, strategic buyouts and a strong commitment to technology. Southern Glazer’s has turned supply logistics into an advantage, giving producers access to more customers and helping retailers get the right stock exactly when they need it. It’s a combination of traditional know-how and data-driven precision. Whether it’s wine, spirits or anything in between, Southern Glazer’s brings a level of order to the beverage alcohol market that’s rare in an industry still fond of handshakes and heritage labels.

That said, even in a space that often leans on legacy and gut instinct, the company is proving that AI has a place—if introduced the right way.

Diego Fonseca, Vice President of Inbound Supply Chain and Logistics at Southern Glazer’s, lays it out plainly: “Everything starts within our own organisation. Implementing AI is a journey that requires not only best fit technology, but most importantly, the right goals and strong change management to be successful,” he says. 

Diego covers the forecasting, analytics, purchasing and delivery of products coming from the company’s suppliers into its warehouses. Convincing stakeholders both inside and outside the company means showing them the data. When winemakers and distillers see hard numbers that prove AI delivers results, they start to back the tech and even bring it into their own processes. 

There’s a broader context to this shift, too. Mark Wilkinson, Senior Vice President of the Business Division Unit at OpenText, sees the move to AI forecasting as part of a larger evolution across business sectors. 

“The business world is becoming more AI-driven every day, making AI forecasting models pivotal for strategic success,” he says. Mark’s role involves steering OpenText’s global business network operations while ensuring internal technology decisions enhance how the company runs and how it advises clients.

It’s about building expertise that customers can trust—but trust is no small matter when companies are grappling with a data tsunami. Traditional methods just aren’t cutting it anymore. Firms are overwhelmed by the sheer scale of information flowing in daily and without the right tools, key insights can easily slip through the cracks.

That’s where OpenText steps in. It offers systems that capture, govern and move information securely across the globe. More than just managing data, the company’s goal is to help businesses reimagine how they use information. 

Southern Glazer’s and OpenText are coming at the problem from different angles, but they’re solving the same core challenge – how to use data not just to react, but to lead. In a market that moves quickly and relies on consistency, that’s essential. 

Data-driven resilience in a volatile market

Navigating global alcohol distribution comes with its fair share of complications as regulatory shifts, tariffs and climate events all introduce a level of unpredictability that makes long-term planning difficult. 

For Southern Glazer’s Wine & Spirits, staying ahead means not only understanding these risks but having the tools in place to respond to them in real time. The company leans into agility and data-driven decision making as the foundation of its supply chain strategy, especially when external forces disrupt operations.

“Supply chain disruption is a topic that is at the centre of supply chain innovation these days, as organisations build integrated control towers,” says Diego. He points to COVID-19 as a major wake-up call for the industry. The pandemic exposed weaknesses in global supply chains, particularly the lack of real-time visibility and flexible infrastructure. “The keys to remaining resilient under these types of external factors are agility and smart decision making.” 

To counter these challenges, Southern Glazer’s has developed a set of analytics dashboards designed for fast interpretation and execution. These tools help the company coordinate with suppliers and distribution centres, optimising inventory and delivery routes in response to changes. 

Now, the next step is layering AI into these systems. By connecting the various data points that already exist - shipment timing, warehouse status, product demand and more—AI promises to enhance decision speed and accuracy across what Diego refers to as a “control tower platform.” This move turns isolated insight into integrated action, helping the company adapt to regulatory changes, manage cost fluctuations from tariffs or respond to delayed harvests caused by shifting weather patterns.

On the technical front, the challenge of applying AI across markets lies in the data itself. Mark is blunt about what’s needed: “To get the true value from AI’s forecasting capabilities, the business should have access to high-quality, accurate data.”

If the raw information isn’t clean, no algorithm can produce meaningful predictions. Testing that data by checking format compatibility, removing duplicates and balancing values is essential. Only then can businesses trust what the model returns.

Southern Glazer’s has already seen the impact of AI on its inventory processes. While it doesn’t manufacture products, it still needs to avoid overstocking or understocking—a tough ask when customer behaviour shifts week to week.

Diego points to AI-driven forecasting as a way to reduce bias in ordering decisions. “With the use of AI, we saw improvement in our forecasting BIAS metrics as human sentiment is taken out of the equation. This is helping us tremendously with significant inventory reductions as we place more accurate orders perpetually.”

OpenText is also seeing early movement in this area, although the company is still building out full applications of AI forecasting. Mark sees the current phase as just as vital: “We’re enabling eventual smarter decisions by cleaning and preparing our customers’ data for deeper application; AI is useless, after all, if the data and information models used to forecast are not clean, accurate and complete.” 

Regional patterns and global challenges

When it comes to alcohol consumption, there’s no one-size-fits-all approach—regional preferences, cultural events and shifting trends mean demand can swing dramatically. Geographical variation in drinking habits further complicates global alcohol distribution. 

According to the World Health Organization (WHO), European countries—particularly Czechia, Latvia and Moldova - top the global chart in alcohol consumption per capita. By contrast, consumption remains very low in many Middle Eastern and North African countries. These regional variations demand nuanced forecasting models that consider far more than simple averages.

For Diego, this complexity is precisely where AI shows its worth. “Capturing patterns that are not straightforward to be observed is one of the key advantages brought by AI,” he explains.

That said, it takes months of work with data scientists to make the models function effectively. Diego outlines a technique his team applies known as time series decomposition. This statistical method breaks down sales data into its underlying components: trend, seasonal, level and residual. In doing so, Southern Glazer’s can detect item and location combinations that show strong seasonality and reclassify them into targeted clusters. These decomposed components are then used as explicit inputs in the AI model, giving it visibility over recurring spikes and dips that simpler models might miss. 

At OpenText, Mark points to predictive AI as an essential tool for building resilience into supply chains, stating “the business world is evolving as rapidly as ever.” 

However, he stresses that clean, reliable data is key: “A major difficulty arises from partners with separate data management processes, resulting in differently formatted data.” If inconsistencies and errors aren’t dealt with, such as duplicates or mislabelled values, then AI systems risk returning misleading outputs. Mark calls this risk “hallucinations,” where the AI appears to provide confident forecasts that are, in fact, inaccurate due to faulty data inputs.

Meanwhile Gallup’s 2022 report shows a noticeable shift in drinking patterns across generations. In the US, only 62% of adults under 35 reported drinking alcohol in 2021, down from 72% in 2001. 

“These trends are playing an important role on our long-term forecasting parameters,” Diego says. This trend is being picked up by Southern Glazer’s AI models, which now analyse up to 36 months of data and project up to 24 months ahead. As forecasts for core categories like beer or spirits trend downwards, the company sees greater innovation activity—particularly in non-alcoholic options.

“Innovation forecasting is an area we are working on,” Diego explains. “It is much harder to generate a forecast for something with no history.” Yet by training models to detect emerging patterns, Southern Glazer’s aims to stay ahead of evolving preferences, particularly as younger generations reshape the market with changing expectations.

The next era of demand prediction

As the pace of technological change accelerates, the future promises a major shift in how forecasting is approached in the alcohol distribution sector. 

Diego envisions a system where forecasting becomes largely autonomous—what he calls a “touchless forecasting process.” In this future model, human input will still play a role, but it will come at the start of commercial planning rather than being used to retroactively adjust figures to meet goals. AI will do the heavy lifting, constantly scanning the web for emerging consumption trends, analysing data in real time and shaping forecasts without manual interference.

He anticipates a setup where commercial teams will focus on pricing strategies and planning event-driven campaigns to influence demand, while the AI generates the forecast entirely based on up-to-date information. These forecasts won’t be static either as demand sensing agents (automated systems that react to changes in shipment data and customer inventory levels) could refine the forecasts daily or weekly.

Mark shares Diego’s optimism, but sees agentic AI as the gamechanger. “Its autonomous capabilities reflect a new era in global business operations,” he explains. He foresees a data sharing and regulatory compliance revolution as it streamlines processes and reduces friction in international supply chains.

Looking ahead to 2035, Mark believes the next decade will mirror the last in terms of unforeseen innovation. 

“This trend of automation across industries is set to continue,” he concludes, “with agentic AI proving to be both efficient and profitable.”

To read the full article in the magazine, click HERE.