Traditional unconstrained demand estimation methods in airline industry only address the spillover and recapture problem of customer demand in parallel nonstop flights，and fail to consider the substitution effects in airline networks between direct and connecting flights． Based on the ranking list of customer preferences，customer type set in airline network is defined． Meanwhile，a network nonparametric discrete choice model considering strategic customer behavior is developed． In light of the incompleteness of the historical booking data in network environment，from the perspective of online and offline trading platforms，the complete data log-likelihood functions under the conditions of uncensored and censored demand are established respectively． The EM algorithm is applied to jointly estimating customer arrival rate and the probability mass function． After that，the unconstrained estimation calculation methods of primary demand，recapture demand as well as spillover demand of customers in airline network are proposed． The feasibility and effectiveness of the proposed methods are verified by numerical simulations． Compared with the existing methods，our methods can accurately reflect the impact of substitution effects in networks between products on customer choice behavior，and thereby more effectively avoid overestimating the primary demand of historical customers．