ALG supported SANS in the development of a comprehensive Data & AI strategy to scale and industrialize data-driven products across the organization. The work built on an existing analytics platform that had already enabled several high-value use cases, aiming to unlock further value through a more structured and scalable data management approach.

ALG assessed the current state of the Data Management Directorate, reviewing the technology stack, implemented use cases, key achievements and organizational setup. Benchmarking against leading ANSPs helped identify gaps and define improvement priorities aligned with industry best practices.

Based on these insights, ALG defined a three-year vision for the Directorate, including strategic objectives aligned with corporate priorities and a structured KPI framework. The team designed the target technology stack, considering functional requirements, costs and risks, and developed a workforce and talent plan covering capability needs, upskilling and sourcing strategy.

ALG also defined a Data Realisation roadmap, outlining key initiatives to drive adoption and value creation. The strategy was validated through engagement with C-level stakeholders, ensuring alignment, commitment and a clear path to implementation and organizational transformation.

ALG supported EASA in the design, implementation and operation of the Data4Safety (D4S) platform, one of the largest collaborative aviation safety data initiatives globally. The work enabled the transition from reactive to proactive safety management by leveraging integrated, cross-industry data to identify risks and support evidence-based decision-making across the European aviation network.

ALG designed and deployed a cloud-based Big Data platform covering the full data lifecycle, integrating multiple data sources such as Flight Data Monitoring (FDM), air traffic data (ADS-B), safety reports, weather information and contextual exposure data. This provided a unified and scalable foundation for advanced analytics across traditionally siloed datasets.

The team developed a range of data products, including KPI computation pipelines, interactive dashboards and advanced analytics solutions such as machine learning models for use cases like CO₂ estimation. Close collaboration with airlines, ANSPs, CAAs and manufacturers ensured alignment with operational needs and regulatory requirements.

In addition, ALG implemented business intelligence and visualization capabilities to deliver performance dashboards, including blind benchmarking features that allow organizations to compare their performance against industry peers. This approach strengthened transparency, continuous monitoring and data-driven safety improvements across stakeholders.

ALG supported EASA in the development of an AI-based demonstrator for CO₂ emissions estimation, contributing to the implementation of an EU-wide environmental labelling approach under the RefuelEU Aviation regulation. The work helped address the challenge of estimating future emissions, complementing the use of historical airline data for sustainability reporting.

We defined analytical methodologies to estimate CO₂ emissions during the cruise phase of commercial flights, leveraging aviation data available in the Data4Safety (D4S) Big Data platform. This included the design of data models and feature engineering approaches to transform raw flight data into meaningful inputs for predictive modelling.

ALG developed and tested machine learning-based demonstrators, covering data pre-processing, model implementation, training and validation. The prototype was deployed in a cloud-based environment to assess scalability and integration with existing data infrastructure.

The work resulted in a functional demonstrator capable of estimating CO₂ emissions for future scheduled flights, enabling EASA to assess the feasibility of predictive emissions modelling. It also contributed to building internal capabilities and practical know-how in applying AI in line with EASA’s machine learning guidance.

ALG supports a major hub airport in the Middle East in defining and activating a comprehensive Data & AI strategy to enhance decision-making across operations and commercial functions. The work helps the client assess its current data maturity, identify high-value use cases and establish a clear roadmap to scale data-driven capabilities in line with its digital transformation ambitions.

We assess the existing Data & AI landscape, covering systems, data quality, governance, processes and workforce readiness, while mapping core platforms such as AODB/AMS, BHS, ERP and commercial systems. Through stakeholder engagement, we capture key business needs and translate them into a prioritized portfolio of Data & AI use cases.

Building on these insights, we design the target operating model and governance framework and define a structured “use case factory” approach to identify and scale AI initiatives continuously. The engagement also includes the definition of a multi-year strategy and implementation roadmap, covering technology architecture and foundational enablers.

To ensure early impact, ALG supports the activation of key data capabilities and the delivery of three quick-win solutions: passenger forecasting, passenger segmentation, and commercial sales forecasting enhanced with GenAI.

ALG developed ADAPT, an Aviation Intelligence Platform that combines ADS-B and operational datasets with proprietary analytical models to deliver advanced insights for aviation stakeholders. The solution leverages automated data pipelines and industry expertise to support both strategic and operational decision-making across 30+ projects.

ADAPT integrates multiple data sources, including flight trajectories (ADS-B), airport and runway information, airspace structures, schedules, and weather data, enabling enriched analytics and the computation of advanced operational metrics beyond standalone datasets.

Representative applications include:

1- Tocumen Airport (Panama): Supported capacity assessments by benchmarking ASMA additional time against peer airports, identifying future congestion risks and infrastructure bottlenecks.

2- Cayman Islands Airspace: Enabled estimation of airspace usage by analysing distance travelled per route and aircraft type, supporting fare strategy design despite limited tracking capabilities.

2- Heraklion Airport (Crete): Analysed waypoint usage and altitude profiles within the TMA, providing insights into traffic flows and operational behaviour during arrivals and departures.

Overall, ADAPT strengthens data-driven decision-making by delivering scalable, high-value analytics across diverse aviation contexts.

ALG supported Aeromexico in the development and integration of machine learning capabilities to enhance operational predictability and efficiency at its main hub, Mexico City International Airport (AICM), a highly congested environment. The work enabled improved situational awareness and more informed decision-making across both strategic and tactical operational phases.

ALG defined and implemented machine learning use cases tailored to key operational challenges. In the strategic phase, models were developed to identify critical flights with a high risk of causing schedule disruptions, supporting proactive planning and resource allocation. In the tactical phase, ALG designed predictive models to estimate Off-Block Times (OBT) with greater accuracy, improving real-time operational visibility.

The engagement covered the full data science lifecycle, including use case definition, data exploration and acquisition, feature engineering and model development. Algorithms were trained, validated and refined to ensure robustness and reliability, while results were translated into actionable insights for operational teams.

By embedding these capabilities into Aeromexico’s processes, the project strengthened operational efficiency, reduced uncertainty and enabled a more data-driven approach to managing complex airport operations.