Intelligent aggressiveness: Combining forecast multipliers with various unconstraining methods to increase revenue in a global network with four airlines

Airlines are always searching for ways to maximize revenues in the hyper-competitive environment that they exist in. This article uses the sophisticated Passenger Origin-Destination Simulator (PODS) simulator to examine the revenue impact of four levels of forecast multipliers (FM) in combination with three different methods of unconstraining – Expectation Maximization (EM), Projection Detruncation (PD) and Booking Curve (BC). Owing to the competitive nature of PODS (four airlines competing for customers) and its allowance for customer choice, we are able to assess all the implications of these FM levels in combination with unconstraining, including the impact of spill, upgrades and recapture. We find that in this fully/semi-restricted fare environment, under leg optimization and either EM or PD, the optimal level is generally FM of 1.1, independent of demand level, and that under BC unconstraining, the optimal level is FM equal to 1.2. When using realistic booking data from major global airlines to calibrate PODS’ largest global network (U1), we show that becoming more intelligently aggressive with FM can lead to revenue gains of 0.2–0.6 per cent under EM or PD unconstraining and gains of 0.3–1.2 per cent under BC unconstraining. Under network optimization, it is best not to use FM under any unconstraining method, independent of demand level.