With supply chains becoming increasingly complex and unpredictable, the use of data analytics has become essential for making informed decisions. Advanced analytics provides businesses with the necessary tools to enhance forecasting, optimize resource allocation, and mitigate disruptions. In this interview published in The Supply Chain Ledger, Víctor Carballo (Senior Engagement Manager at ALG) shares his insights on how data-driven strategies are transforming supply chain management, offering a first-hand perspective on the transformative power of analytics in improving efficiency and resilience.
With over 15 years of experience in transport and infrastructure consulting, holding roles ranging from Operations Director to Managing Director of Airport Services, Víctor Carballo has built a career focused on optimizing operations, managing risk, and driving efficiency. Additionally, he has developed deep expertise in how advanced analytics can transform supply chain and operations management. In this conversation, he shares his personal perspective on how data and analytics are reshaping the future of supply chains and the key role they will play in enabling smarter, more resilient decision-making.
How are you leveraging data analytics to improve decision-making and operational efficiency in your supply chain?
I have many years of experience using data analytics to enhance decision-making and operational efficiency, especially in supply chain management and operations that require demand forecasting and sizing. Over the years, the capabilities of data analysis have greatly improved, enabling more accurate predictions and providing better insights for decisionmaking. For example, in logistics and air transport, analysing historical data helps forecast future production needs. By incorporating additional factors like holidays or weather conditions, we can refine these predictions even further. Automated production forecasting ensures that timely requests are made to suppliers, improving supply chain efficiency. In an airport environment, predicting demand by combining historical data with flight schedules, holidays, and weather conditions helps optimise resource allocation and streamline operations.
What types of data do you find most valuable in predicting supply chain disruptions, and how do you act on these conditions?
In predicting disruptions within the supply chain, I find real-time data to be invaluable. These data points help us anticipate short-term disruptions and adjust our operations accordingly. In complex environments like airports, accessing real-time information about potential disruptors—such as flight delays, weather changes, or mobility issues affecting access to facilities—is essential. This data allows us to dynamically adjust our resource allocation. For example, if an unexpected flight delay occurs, we can quickly recalibrate our resource deployment, ensuring that the necessary personnel and equipment are available to handle the revised schedule efficiently. Acting swiftly on these insights helps maintain operational continuity and ensures high service levels.
Can you provide an example where advanced analytics helped you optimise inventory levels or improve demand forecasting?
A prime example of advanced analytics in action is managing inventory levels, such as determining the number of baggage carts needed at an airport to meet future operational demands. By using advanced data analysis techniques that combine historical data with mathematical models, we can establish correlations between anticipated flight volumes and resource requirements. My experience has shown that applying polynomial or logarithmic models to analyse data pairs specifically, comparing historical needs against flight volumes—enables us to create highly accurte predictive formulas. These models are customised to the unique operational characteristics of each airport, allowing us to maintain optimal inventory levels, preventing both shortages and excessive surpluses.
What challenges do you face when implementing analytics-driven decision-making, and how do you overcome them?conditions?
The main challenge in implementing analytics-driven decision-making is accelerating the data analysis process so that decisions can be made quickly and effectively. While many organizations can perform targeted analyses with the help of key personnel, automating these analyses and integrating them into daily operational systems remains a challenge. To overcome this, I focus on helping organisations systematize the integration of data analysis into their decision-making processes. This is similar to using navigation tools that adjust routes based on real-time traffic data; in the same way, companies can benefit greatly from using real-time analytics to adapt their operations. Although setting up such systems may take more time upfront, the potential to prevent costly disruptions justifies the investment.
How do you see the role of data and analytics evolving in the future of supply chain management?
I envision the role of data and analytics becoming increasingly central to the future of supply chain management. As real-time data integration becomes more commonplace—much like how GPS navigation has become integral to driving—companies will increasingly rely on continuous data analysis to enhance their operational decisions. This evolution will lead to the development of more sophisticated analytics platforms that can seamlessly integrate with existing management systems, enabling companies to leverage data for strategic planning and operational adjustments. The ability to predict and mitigate disruptions before they occur will not only streamline operations but also significantly improve overall supply chain resilience.
