Aviation readiness isn’t measured on a dashboard. It’s measured on the flightline, by aircraft availability, maintenance turn around time, and how often teams are forced into reactive decisions.
In defense aviation environments, even small delays in signal timing or inventory alignment can ripple into grounded aircraft and missed mission windows.
For Dr. Sridhar “Sri” Dandapanthula, Principal Data Scientist on SteerBridge’s Aviation Technology Team, that reality shapes how data science is applied to aviation logistics challenges. Analytics are only valuable when they reduce friction in real workflows, helping maintenance and supply teams act earlier and with fewer surprises.
Sri’s work reflects how SteerBridge supports aviation readiness across complex, data-rich, and operationally constrained environments, by connecting fragmented information, applying analytics with discipline, and staying focused on outcomes at the point of execution.
Defense aviation logistics operate across multiple systems, stakeholders, and timelines. Maintenance records, flight-hour data, supply inventories, and usage patterns are often stored in separate platforms, updated on different schedules, and governed by different processes.
Individually, each dataset tells part of the story. Together, they reveal where readiness risks are forming, if the data can be aligned in time.
In practice, those connections are not always easy to see.
Inventory decisions are frequently influenced by historical habits rather than forward-looking demand signals. Parts may be stocked out of habit, not because they are most likely to be needed next. Maintenance actions become reactive, driven by failures already experienced instead of those that could have been anticipated.
The result is familiar across aviation programs:
• Critical components unavailable when needed
• Excess inventory tied up on shelves
• Longer repair cycles and unplanned removals
• Increased down aircraft events that strain budgets and schedules
These challenges are rarely caused by a lack of data. They stem from how data is integrated, interpreted, and applied in time to influence day-to-day execution.
Sri’s background spans commercial-scale analytics environments and defense sustainment settings, where data is put to the test under operational constraints.
Earlier in his career, Sri saw firsthand what it takes to move analytics from concept into production. While at Microsoft, Sri worked on an algorithm developed during a hackathon that was ultimately selected and deployed to detect fraudulent activity in online storefronts. That experience reinforced a standard he still applies today. Analytics only matter if they survive real-world use.
Sri joined Boeing without any formal aerospace background and had to learn the ropes quickly. He succeeded by leveraging his strong mathematics and data foundations, along with his strong flexibility to adapt to the new field. He spent his first two years supporting commercial aircraft programs including the 777and 787, before transitioning to government aviation programs supporting platforms such as the Apache helicopter, KC-46 tanker, and the F-15 and F-15EX.That experience grounded his analytics work in how aviation systems are actually maintained, supplied, and sustained.
Within Boeing Global Services, Sri’s focus expanded into aftermarket analytics supporting extended warranties and sustainment service offerings. His work included spare parts forecasting, identifying discrepancies in customer purchasing behavior, and building analytical case studies to justify additional services. Several of these algorithms were recognized internally as proprietary intellectual property and presented to executive leadership.
At SteerBridge, Sri applies those lessons in closer proximity to operations. He has visited military bases and observed how maintenance, supply, and logistics systems are used in real operational environments. Seeing how data-driven tools affect readiness at the point of execution has reinforced his focus on timing, usability, and reliability rather than theoretical performance.
In aviation logistics, that means focusing less on theoretical model accuracy and more on whether insights arrive early enough to be useful. A highly accurate forecast that arrives too late does little to prevent a grounded aircraft.
By working directly with maintenance, usage, and supply data, Sri helps reduce uncertainty where it matters most, supporting earlier signals, smoother workflows, and fewer last-minute surprises that disrupt readiness.