All Work
Azul Airlines AI Network Planning - $6M Weekly Revenue Gains with AI-Driven Network Planning hero image

Azul Airlines AI Network Planning

Financial ServicesOverview

Azul Airlines AI Network Planning

$6M Weekly Revenue Gains with AI-Driven Network Planning

TL;DR

  1. The solution is: Azul Airlines achieved $6M weekly revenue gains by replacing intuition-based network planning with AI-driven causal inference and real-time financial visibility

  2. Reduced financial reporting lag from 2-3 months to instant analysis using a ticket-to-financial clarity product built on live operational data

  3. Added 500+ profitable flights in non-obvious markets using Double ML causal inference and an ensemble of 9 combined models, while achieving 25% fare increases through systematic data-driven pricing optimization

The Challenge

Airlines make billion-dollar decisions about which routes to fly, how much capacity to deploy, and what prices to charge. Traditionally, these decisions rely heavily on executive intuition and quarterly financial models that arrive 2-3 months after the fact. By the time you understand what happened last quarter, market conditions have already shifted.

Azul Airlines, Brazil's third-largest carrier, faced exactly this challenge. Network planning decisions lacked quantitative validation. Financial visibility lagged by months. The company needed to answer fundamental questions: which new routes would actually be profitable, how to price tickets when demand patterns shift, and what the real-time financial impact of today's decisions actually was.

The core problem was that Azul could see correlations in historical data but couldn't validate causal relationships. Would adding a flight to a new market generate profit, or would it cannibalize existing routes? Traditional business intelligence tools couldn't answer this. The solution required causal inference, not just correlation analysis.

The initial team working on AI solutions was just 5 people facing resistance from decision-makers who relied on decades of industry experience, creating a trust gap that was as much a cultural challenge as a technical one.

Key Results

  • $6M weekly revenue gains across AI strategy initiatives (reported by Aviation Week, February 2026)

  • 25% fare increases through systematic data-driven pricing optimization

  • 500+ profitable flights added in non-obvious markets

  • 2-3 month financial reporting lag eliminated, replaced with real-time visibility

  • 1M-2M BRL generated in first two weeks from Markets Ranked system

  • Active user base grew from 5 to 10+ stakeholders within 9 months

The Solution

01

Cutting the Reporting Lag From Months to Instantly

Finance teams at Azul used to wait months to understand whether a pricing decision had worked. We built a system that converts live ticket sales into a full financial picture every day. Leadership can now see the impact of pricing changes, route adjustments, and capacity decisions as they happen rather than in a quarterly report. This shift from waiting to knowing enabled Azul to test pricing strategies systematically and adjust quickly when something was not working.

02

Answering the Counterfactual Question

Knowing that a route performed well is useful. Knowing whether it would have performed well regardless of your decision is more useful. Traditional analysis cannot answer that question. We used a two-stage statistical technique that separates the effect of a decision from outside factors like seasonality, competitor behaviour, and economic conditions. This let Azul's planning team validate network decisions with confidence intervals rather than gut feeling.

03

Nine Models Working Together for More Reliable Forecasts

No single model is perfect. We built an ensemble of nine models that each capture different aspects of airline revenue. When the models agree, confidence is high. When they diverge, the system flags uncertainty and identifies what is driving the difference. This approach helped Azul find over 500 profitable flights in markets that traditional analysis would have overlooked.

04

Building Credibility Before Proposing Anything New

When the project started, five people at Azul were using the AI tools. Executives with decades of experience were sceptical. We spent the first phase validating what the team already believed, using the causal analysis system to explain why certain routes had performed well or poorly. Every recommendation came with an explanation and a confidence range. Quick early wins built credibility. By the end of the initial nine months, over ten stakeholders were incorporating model recommendations into their decisions.

Results

Key Metrics

  • $6M weekly revenue gains across AI strategy initiatives (reported by Aviation Week, February 2026)

  • 25% fare increases through systematic data-driven pricing optimization

  • 500+ profitable flights added in non-obvious markets

  • 2-3 month financial reporting lag eliminated, replaced with real-time visibility

  • 1M-2M BRL generated in first two weeks from Markets Ranked system

  • Active user base grew from 5 to 10+ stakeholders within 9 months

The Full Story

The AI systems transformed network planning from intuition-driven to data-driven across Azul's operations. The $6M weekly revenue gains span AI strategy initiatives including revenue management, network planning, and maintenance systems, as reported by Aviation Week in February 2026.

Azul achieved 25% fare increases through systematic data-driven pricing optimization using real-time PNL forecasts, replacing guesswork with validated, data-backed decisions. The ensemble models and causal inference systems identified 500+ flights added in non-obvious markets that traditional analysis would not have prioritized.

The 2-3 month financial reporting lag was eliminated entirely, replaced with instant analysis that enables faster decision-making at every level of the organization. Counterfactual analysis capabilities now quantify the expected impact of network changes before implementation, giving leadership confidence in decisions that previously relied on intuition.

The project completed within 9 months of the 2-year engagement scope. The systems continue to run daily, producing updated recommendations as market conditions evolve.

Conclusion

In summary, Azul Airlines transformed from flying blind on network decisions to making data-driven choices backed by causal inference and real-time financial visibility. As a result, the $6M weekly revenue gains, 25% fare increases, and 500+ new profitable flights demonstrate the business impact of production AI systems built for operational decision-making, not just analysis.

The cultural shift from intuition-based to data-driven decision making represents the deeper transformation, one that positions Azul to adapt quickly as market conditions evolve. Furthermore, as airlines face increasing complexity in network planning, pricing optimization, and capacity allocation, the systematic approach Azul pioneered offers a roadmap for turning AI from a buzzword into a competitive advantage.

Key Insights

  1. Start with real-time visibility before optimization. Eliminating Azul's 2-3 month reporting lag enabled systematic testing of pricing strategies that led directly to 25% fare increases.

  2. Use causal inference, not just correlation, for high-stakes decisions. Double ML enabled Azul to validate network planning decisions quantitatively, replacing intuition with data-driven counterfactual analysis.

  3. Ensemble modeling increases reliability for production systems. Combining 9 models provided robust recommendations and identified 500+ profitable flights that single models would have missed.

  4. Build trust gradually through validation, not just recommendations. Starting with 5 skeptical stakeholders, Azul grew to 10+ active users by validating existing decisions before proposing new ones.

  5. Quick wins accelerate organizational buy-in. The 1M-2M BRL generated in the first two weeks from the Markets Ranked system demonstrated immediate value and built credibility for broader adoption.

  6. Admit uncertainty to build long-term trust. Showing confidence intervals and flagging model disagreement proved more valuable than overpromising, establishing AI tools as reliable decision support.

  7. Daily model updates matter for operational decisions. Running models on fresh data daily meant network planners worked with current insights, not stale quarterly reports that lag market conditions.

Key Terms

Double ML (Double Machine Learning)
Double ML is defined as an econometric technique that combines machine learning with causal inference by using two model stages to debias treatment effect estimates, enabling counterfactual analysis — answering what would have happened under a different decision.
Causal Inference
Causal inference refers to the statistical process of determining whether a relationship between variables is causal rather than merely correlational, allowing decision-makers to predict the true impact of a choice rather than pattern-matching on historical data.

Implementation Details

01

Ticket-to-Financial Clarity: Eliminating the Reporting Lag

The first system we built converts ticket sales data into a comprehensive financial picture using live data from Azul's operational systems. Previously, finance teams waited for quarterly models to understand profitability. The new system eliminated that 2-3 month lag entirely, giving leadership real-time visibility into the financial impact of pricing decisions, route changes, and capacity adjustments.

The system includes a PNL forecast correction module that uses real-time data to adjust profit and loss forecasts dynamically. Instead of relying on stale quarterly assumptions, the model updates daily as new ticket sales, fuel prices, and operational costs flow through.

We built the system on AWS and Snowflake infrastructure to handle Azul's operational data volume. The key innovation was speed. By eliminating the months-long delay in financial visibility, Azul could test pricing strategies systematically, increase fares in specific markets, observe the real-time revenue impact, and adjust quickly if demand dropped. This systematic approach contributed directly to the 25% fare increases Azul achieved.

02

Double ML Causal Inference for Network Decision Validation

Correlation doesn't equal causation, and that's the core challenge in airline network planning. Azul could see that certain routes performed well historically, but couldn't answer the counterfactual question: what would have happened if capacity had been allocated differently? Would a new route generate incremental revenue, or just shift passengers from existing flights?

We implemented Double ML (Double Machine Learning) to extract causal information from correlational data. Double ML combines machine learning with econometric causal inference to estimate treatment effects while controlling for confounding variables like seasonality, competitive pricing, economic conditions, and network effects.

This enabled quantitative validation of network planning decisions. Instead of debating whether a new route would work based on intuition, stakeholders could see model predictions with confidence intervals. The causal inference system became the foundation for the Markets Ranked by Overall Score product, which ranks thousands of potential airline markets for capacity allocation using ML-driven scoring that accounts for causal relationships, not just historical correlations.

In the first two weeks after deployment, the Markets Ranked system generated 1M-2M BRL by identifying optimal network expansion opportunities that weren't visible through traditional analysis.

03

Ensemble Modeling: 9 Models for Robust Recommendations

No single model is perfect. Different modeling approaches capture different aspects of airline revenue dynamics. We built an ensemble system combining 9 models: 3 prediction models and 3 causal models, each with variations. The prediction models forecast demand and revenue using time series analysis, gradient boosting, and neural networks. The causal models estimate treatment effects using different econometric approaches.

The ensemble combines these models to produce robust revenue predictions and network optimization recommendations. When models agree, confidence is high. When they diverge, the system flags uncertainty and identifies which factors are driving the disagreement. This uncertainty quantification was critical for building trust with leadership, who needed to understand both upside potential and downside risk.

This ensemble approach enabled Azul to identify 500+ profitable flights in non-obvious markets during high season. These weren't routes that traditional analysis would have prioritized. The models identified market opportunities where demand patterns, competitive dynamics, and network effects aligned favorably.

The system runs daily on AWS infrastructure, processing updated operational data and producing fresh recommendations. We built comprehensive monitoring and validation pipelines to catch data quality issues, model drift, and prediction anomalies before they impact business decisions.

04

Building Trust: From 5 Skeptics to Organizational Buy-In

The hardest part wasn't building the models. It was changing the culture. When we started, 5 people at Azul were actively using the AI tools. Executives had decades of airline industry experience and trusted their intuition.

We took a systematic approach to building trust. We started with validation rather than recommendations, using the causal inference system to explain why certain routes performed well or poorly, confirming or challenging existing hypotheses before proposing anything new. Every recommendation included explainability: why did the model rank this market highly, what factors drove the prediction, and what was the confidence interval.

Delivering quick wins mattered. The 1M-2M BRL generated in the first two weeks from the Markets Ranked system demonstrated immediate value and built credibility. When models disagreed or confidence was low, we said so. This honesty built trust more than overpromising would have.

By the end of the 9-month initial project phase, the user base had grown from 5 to over 10 stakeholders, with network planning decisions increasingly incorporating model recommendations alongside executive judgment.

References & Further Reading

Frequently Asked Questions

Double ML (Double Machine Learning) enables counterfactual analysis by isolating the causal effect of network decisions from confounding variables using a two-stage debiasing process. The technique uses one set of machine learning models to predict nuisance parameters (confounders) and another to estimate the treatment effect, allowing Azul to answer questions like 'What would revenue have been if we hadn't opened this route?'

This approach was critical for Azul because traditional correlation-based analytics couldn't distinguish whether a route performed well due to the decision itself or external factors like seasonality, competitor actions, or economic conditions. By providing true causal estimates rather than correlations, Double ML gave leadership confidence that AI recommendations would actually drive the predicted outcomes, overcoming skepticism about black-box AI systems.
Azul achieved measurable revenue gains within 6-9 months of initial implementation, with the $6 million weekly revenue increase realized after full deployment across network planning decisions. The project followed a phased approach: 3 months for data infrastructure and model development, 2-3 months for pilot testing on select routes, and another 3-4 months for full-scale rollout.

The rapid ROI was enabled by Azul's decision to layer the AI system over existing infrastructure rather than replacing legacy systems. This meant the team could start generating insights and recommendations immediately while legacy processes continued running in parallel. Early wins during the pilot phase, including successful route optimizations and pricing adjustments, built organizational confidence and accelerated adoption across the network planning team.
The key to overcoming cultural resistance was demonstrating transparency through causal inference rather than asking executives to trust black-box predictions. By using Double ML to show not just 'what to do' but 'why this decision will work' with counterfactual analysis, the team gave leadership visibility into the reasoning behind AI recommendations.

Additionally, the approach respected existing expertise by positioning AI as augmenting rather than replacing human decision-makers. Network planners could see how the system incorporated their domain knowledge while removing cognitive biases and processing vastly more scenarios than humanly possible. Starting with a pilot program on select routes also allowed skeptics to see real results before committing to full adoption, building trust incrementally rather than demanding a leap of faith.
An ensemble of 9 models provides superior accuracy and robustness by capturing different aspects of airline revenue dynamics that no single model can fully represent. Each model in the ensemble specializes in different patterns, some excel at capturing seasonal trends, others at competitor responses, and others at demand elasticity, and their combined predictions are more reliable than any individual model.

For Azul's high-stakes network decisions involving millions in revenue, the ensemble approach also reduces the risk of model failure. If one model performs poorly due to unexpected market conditions, the other eight compensate, providing stability. The ensemble also enables uncertainty quantification, giving decision-makers confidence intervals around predictions rather than single point estimates, which is critical when leadership needs to understand both upside potential and downside risk.
The real-time financial forecasting system provides financial visibility within hours of ticket sales, compared to the weeks or months required by traditional airline financial reporting. This near-instantaneous feedback loop allows network planners to detect underperforming routes or pricing strategies quickly and make corrections before significant revenue is lost.

The speed is achieved through a modern data architecture that ingests booking data continuously and runs incremental model updates rather than batch processing. This real-time capability was transformative for Azul because airline revenue management requires rapid iteration, fare adjustments, capacity changes, and promotional decisions must respond to market conditions within days, not quarters. The system essentially turned financial forecasting from a retrospective reporting function into a proactive decision-support tool.
The systematic pricing optimization approach used causal inference to identify routes where demand was price-inelastic, meaning customers would pay significantly more without reducing booking volumes. Rather than applying blanket price increases, the AI system analyzed historical elasticity patterns, competitive dynamics, and customer segmentation to pinpoint specific route-time combinations with pricing power.

The 25% fare increases were implemented gradually with continuous monitoring to validate that demand remained stable. The Double ML framework provided counterfactual analysis showing what revenue would have been at old prices versus new prices, proving the strategy's effectiveness. This data-driven approach eliminated the guesswork and risk aversion that typically constrains airline pricing decisions, allowing Azul to capture revenue that was previously left on the table due to conservative pricing assumptions.
Validation is built into the system through continuous counterfactual analysis using Double ML, which compares actual outcomes against what would have happened without the AI recommendation. For every implemented decision, whether opening a route, adjusting capacity, or changing prices, the system maintains a causal model that estimates the counterfactual scenario, providing a rigorous before-and-after comparison.

This approach goes beyond simple performance tracking because it accounts for external factors. For example, if a new route performs well during a strong economic period, the counterfactual analysis determines how much of the success was due to the route decision versus favorable market conditions. This validation methodology was essential for maintaining leadership trust and continuously improving the AI models based on real-world performance feedback.
Yes, the AI approach was specifically designed to layer over Azul's existing airline systems without requiring replacement of legacy infrastructure. The system integrates with existing booking systems, revenue management platforms, and operational databases through API connections and data pipelines, functioning as an intelligent decision-support layer rather than a system replacement.

This architectural choice dramatically reduced implementation risk, cost, and timeline compared to rip-and-replace approaches. Azul could continue operating with proven legacy systems while gradually increasing reliance on AI recommendations as confidence grew. The layered approach also made the project feasible from a change management perspective, as it didn't require retraining staff on entirely new systems or disrupting daily operations during implementation.
OverviewFinancial Servicesintermediate12 min readArtificial IntelligenceAviationNetwork PlanningRevenue OptimizationCausal InferenceDouble MLReal-time ForecastingMachine Learning

Published: · Last updated:

Ready to build something amazing?

Let's discuss how we can help transform your ideas into reality.

Start a ProjectView More Work
How Azul Airlines Gained $6M Weekly with AI Network Planning