the online bipartite graph matching problem has attracted substantial research attention as many real-life problems can be eventually reduced to it.In this work
we study the classic online matching problem that was initially investigated by Karp in 1990.We adopt the
Beta
distribution as the prior distribution of the adjacency relation among the nodes
and present a novel measure to evaluate the matching policy.We also design
Beta
OM
a
Beta
distribution based online matching algorithm
and mathematically prove its soundness.Experiments with
Beta
OM as well as the benchmark algorithms on both synthetic and real data demonstrate that the proposed