Optimal Network Pricing for Oblivious Users under Projected Decision-Dependent Distributions

Efficient large-scale network allocation requires data-driven pricing mechanisms that internalize the stochastic and non-linear dynamics of user behavior. We move beyond the classic fully strategic agents to study oblivious users (agents with bounded rationality and imperfect information). Rather than assuming an infinite horizon, our regime more faithfully reflects real-world network user behavior by acknowledging that large-scale network flows, shaped by volatile human decisions, are too transient to reach an equilibrium among users. We introduce a novel Optimal Network Pricing (ONP) problem for such users, which induces Performativity: a Decision-Dependent (DD) environment where pricing decisions endogenously shift the flow distribution. Without a closed-form distribution, the platform must learn optimal prices from sampled responses. This setting introduces a new challenge: capacity boundaries and projection operators make the optimization landscape nonsmooth, invalidating gradient-based methods. We show that a widely adopted optimality concept Performative Stability (PS) fails in ONP, collapsing to a trivial solution. We then prove the expected objective has a unique global optimum: the Projected Performative Optimum ({\Pi}PO). Targeting {\Pi}PO is algorithmically hard given the performative and the discontinuous Jacobian. To overcome the challenges, we propose a rigorous {\Pi}PO-targeting framework combining Sample Average Approximation with TR-SQP, explicitly handling the capacity boundaries via the nonsmooth Jacobian. We provide theoretical guarantees on probabilistic convexity, sample complexity and computational complexity. Experiments show that our solver significantly outperforms PS-seeking heuristics and a proposed baseline (improving social welfare by 81% on GEANT), highlighting that properly handling capacity boundaries unlocks substantial gains in social welfare.