Revenue Management with Correlated Demand Forecasting

Many airlines are struggling to survive in today's economy. A crucial contribution to the success of an airline is an e cient management of its revenues. The problem underlying revenue management is for the airline to decide whether to accept customer requests for air travel on a real time basis in order to maximize its expected revenue. Typically, an airline o ers several products (itinerary and fare class combinations) and operates a network of many resources (class cabin in a given ight). Demand forecasting is a crucial component of airline revenue management. Most of the papers in this area consider univariate demand which is then modelled with a statistical distribution, the normal and gamma distributions being the most popular (McGill and van Ryzin 1999; Lee 1990). However, in practice the available capacity is allocated dynamically between di erent products and thus is makes sense to take into account the potential correlations among product demand. At the same time, demand for any single product is recorded over the entire booking horizon at xed time points (snapshots). In this framework it is natural to investigate whether there is correlation among realizations of demand for any individual product in di erent booking periods. Inter product and inter temporal correlations of demand have been documented empirically (McGill 1995). For e ciency reasons, it is therefore important to take them into account in a demand forecasting model.