Case Study: Leading Domestic Airline Catering achieves revenue-maximizing fares with Palisade NeuralTools

NeuralTools Assists Airline to Determine the Most Profitable Price Points

Leading Domestic Airline Catering, a Costa Rica–based carrier serving the tourism market, needed a reliable model to predict passenger demand and price elasticity so it could set the most profitable fares. Palisade supplied its NeuralTools neural‑network application to build that predictive capability and analyze how route, date and competitive factors influence bookings.

Palisade consultant Fernando Hernandez trained a NeuralTools model on 143,000 historical ticket records with 21 input variables (80% train / 20% test) and ran a sensitivity analysis that highlighted top drivers (Strength 15.6; Weekday 4.1944; Destination Airport 4.032). The resulting 30‑day route model predicted occupancy versus fare and identified an optimal mean fare of about $174 that maximized revenue to $3,848 with an average of 22 passengers; demand fell sharply past $175 and dropped below five passengers above $185. Palisade’s NeuralTools therefore enabled the airline to determine and adjust the most profitable price points based on measurable demand elasticity.