Today airlines' ancillary pricing decision-making is mostly manual, where prices are generally determined by analysts through competitor benchmarking and historical data analysis. After manual computation, ancillary prices are filed in ATPCO (Airline Tariff Publishing Company) or Merchandising systems and these prices can be further tailored to the characteristics of the ancillary request through merchandising rules. Using airline ancillary and itinerary data, we built a gradient boosting machine algorithm that can understand the intricate relations between numerous attributes such as passenger type, itinerary, aircraft type, ancillary product, or season and can make an automated pricing decision based on science. The analysts are relieved from manual work and have the flexibility to change the machine learning (ML) algorithm's input and output to suit business strategies. The ML algorithm learns the new trends and patterns as part of its training, and analysts can track its performance periodically. The output of the ML algorithm seamlessly integrates with merchandising platforms to implement the dynamic pricing of ancillaries and offers in the direct, indirect, and channels with new distribution capability. The ML algorithm is extendable to airline and third-party ancillary products and ticket bundles. It can suggest an optimal mix of products and price points that have the highest propensity to purchase for a given customer and travel itinerary.