The dynamism of air cargo in Mexico is driving the industry to seek new technological tools to improve decision-making, and predictive artificial intelligence (AI) is beginning to position itself as an instrument to anticipate changes in demand , optimize resources, and avoid disruptions in the logistics chain.
Enrique Mendoza Arce, CEO of enITma , a company specializing in technological solutions for the aviation sector, said that the ability to anticipate how cargo volumes, destinations and space availability will evolve is becoming a key element to maintain operational efficiency.
“Knowing in advance how volumes, destinations, and capacity availability may evolve allows industry players to make decisions before they impact operations,” the executive emphasized.
He noted that Mexico ranked as the third largest international air cargo market in Latin America and the Caribbean during May 2026 , moving 53,000 tons, according to data from the Latin American and Caribbean Air Transport Association (ALTA) , which has increased the operational complexity for airlines, airports and logistics operators, who face the challenge of managing larger volumes of goods in an increasingly demanding environment.
He explained that the efficiency of an airline or airport depends, to a large extent, on its ability to anticipate and respond to events that may affect operations. Hence the importance of knowing and understanding air cargo movements, as it is not only about knowing how much volume is transported, but also about identifying how, when, where, and why demand is changing , since these variations can rapidly modify capacity needs and place greater demands on routes, airports, terminals, and available resources.
The opening of a new plant, he noted, can stimulate demand in a previously underserved corridor , a peak season for e-commerce can boost shipments to certain destinations, and an adjustment in flight frequencies can reduce available capacity just when it is most needed.
In addition, it should be considered that cargo uses both cargo aircraft and available space on passenger flights , so changes in frequencies, destinations and scheduling can alter the available supply.
Given this scenario, predictive artificial intelligence emerges as an alternative to analyze large volumes of information from reservations, airport operations, routes, aircraft capacity and commercial variables, with the aim of detecting patterns and estimating future scenarios.
According to Mendoza Arce, these technologies allow for the identification of early signs of potential changes in logistics flows , facilitating more precise planning of capacity, space allocation, cargo consolidation, and route optimization.
“The ability to relate multiple operational and commercial variables allows us to generate signals about possible changes in cargo flows and support more precise planning,” he explained.
The application of predictive models also strengthens shipment traceability by offering greater visibility into the journey of goods and identifying potential bottlenecks before they affect operations.
However, he cautioned that adopting artificial intelligence does not guarantee results on its own . The effectiveness of these models depends largely on the quality of the available data, the integration between systems, and the ability of organizations to translate the information generated into concrete operational decisions.
In this sense, AI does not replace the experience of operational teams, but rather functions as a complementary tool to detect trends and risks that could go unnoticed through traditional analysis methods.
Comment and follow us on LinkedIn: @GrupoT21
