choice-based demand forecasting in airline revenue management systems PDF
Preview choice-based demand forecasting in airline revenue management systems
CHOICE-BASED DEMAND FORECASTING IN AIRLINE REVENUE MANAGEMENT SYSTEMS Jue Wang This thesis is presented for the degree of Doctor of Philosophy of The University of Western Australia UWA Business School Management & Organisations 2015 To my parents Wei Wang and Guanshu Wang and my Husband Pan Zhang ABSTRACT Over the last decade, airline markets around the world have been reshaped dramatically by the rapidly growing low-cost carriers and new forms of distribution channel. Significant reduction in searching cost brought by the web-based distribution has made fare product comparison and purchasing an easier task. As a result, traditional demand models based on independent (fare class) demand assumption has been violated. A better understanding of passenger choice behaviour is now needed since the development of new generation revenue management (RM) system requires inputs of demand based on dependent fare classes. Early studies on dependent demand mainly focused on the buy-up and buy-down behaviour for single-leg flights. With the introduction of discrete choice modelling, more recent studies are beginning to incorporate competitions between flights and carriers into the model. In a discrete choice model, a customer is assumed to weigh up service levels of a fare product against its price. The fare option with the highest satisfaction is the one being chosen. As all the components taken into consideration by a traveller may not be readily at hand for the analyst, the satisfaction or utility of a fare product is measured by way of a systematic component – the observed utility – and a random component – the unobserved utility. As such, the choice decision is modelled up to a probability. Discrete choice models are theoretically sound for fare product demand forecasting, as they directly work on the decision making process of air travellers. Currently, the most widely applied discrete choice model in revenue management is the multinomial logit model (MNL), within which the unobserved utility of each alternative is independently and identically distributed (IID). Such a structure leads to the independence from irrelevant alternatives or IIA property. That is, the ratio of probabilities for two alternatives is independent from the existence of any other i alternative in the choice set. However, the biggest limitation of IIA is the resulting proportional substitution pattern, which suggests that an improvement in the attributes of one alternative reduces the probabilities for all other alternatives by the same percentage. This highly restricted structure is unlikely to hold in the context of real airline markets. This is because the behaviour of compensatory travellers is likely to vary among the population, and to capture these variations advanced DCMs should be applied. In addition to preference heterogeneity, the decision making process of air travellers are also varying. For example, in RM literature the new priceable/yieldable segmentation was derived on the behavioural difference between the price-oriented (priceable) travellers and the service-oriented (yieldable) travellers. The former would persistently choose the available fare product with the lowest price, while the latter is only interested in a single type of fare product. Although none of the two types of traveller strictly follows the utility maximisation behaviour, they have not been differentiated from the compensatory travellers during choice model estimation. In order to address the above issues, a new stated choice design method was proposed. The use of stated preference (SP) data over the revealed preference (RP) data is because repeated choices from individual travellers that are necessary to identify the decision rule heterogeneity are relatively easy to be obtained under the SP environment. To generate the stated choice experiments, availability design methods were used. Different from traditional labelled experimental designs with fixed choice set composition, availability designs vary the alternatives in a choice set through a ‘master design’, under which the presence and absence of each alternative can be controlled systematically. Such a practice mimics fare product stock-outs caused by the capacity limitation of aircrafts and RM controls utilised by the airlines, but more importantly, it allows the natural correlations between price and service levels to be maintained – a condition ii seldom can be met under fixed-composition design due to attribute trade-offs required by the efficient design criteria. In this thesis, the proposed design has been tested under both simulated and empirical environments. The simulation studies demonstrate the benefit of using availability designs in identifying preference heterogeneity and decision rule heterogeneity in a population. The empirical results show that both preference heterogeneity and decision rule heterogeneity are likely to exist in the real airline market, and they can affect the result of fare class demand in a dramatic way. The thesis provides a proof-of-concept of using RP-SP calibrated choice models for fare product demand forecasting, and proves the importance of air travel choice studies in the development of the new generation choice-based RM system. iii
Description:The list of books you might like
