Guarantee provision in privately financed infrastructure projects implemented as build-operate-transfer/public-private-partnership (BOT/PPP) arrangements is not uncommon in many countries, and Indonesia is no exception. But, given that the government budget is, in most if not all cases, not unlimited, there must be a selection of BOT/PPP projects posing proposals for seeking government guarantees. This paper presents a project selection methodology under the chance-constrained goal-programming framework in the context of the Indonesian BOT/PPP infrastructure industry. The ultimate objective of the selection is to result in a portfolio of guaranteed projects that brings maximum welfare gain to the economy as a whole, maximum total net change in financial net present value but, at the same time, puts the government at the lowest fiscal risk for a given budget constraint. The proposed methodology allows the government to examine relationships among the expected total payment, budget-at-risk allocated, and a desired confidence interval of actual payment not exceeding the budget-at-risk. The government can also compare two or more alternative scenarios and choose the optimal one that delivers the highest value for the money. To illustrate the model application, without sacrificing the generality of the proposed methodology, a much-simplified hypothetical case is presented, examined, and discussed. DOI: 10.1061/(ASCE)CO.1943-7862.0000312. (C) 2011 American Society of Civil Engineers.