AbstractIn this paper, we devise a forward‐looking methodology to determine efficient credit portfolios under the IFRS 9 framework. We define and implement a credit loss model based on prospective point‐in‐time probabilities of default. We determine these probabilities of default and the credits' stage allocation through a credit stochastic simulation. This simulation is based on the estimation of transition matrices. Using data from 1981 to 2019, in a non‐homogeneous Markov chain setting, we estimate transition matrices conditional on the global real gross domestic product growth. This allows considering the effects of the economic cycle, which are of great importance in bank management. Finally, we develop a robust optimization model that allows the bank manager to analyze the trade‐off between the annual average portfolio income and the corresponding portfolio volatility. According to the proposed bi‐objective model, we compute the efficient credit portfolios constructed based on 10‐year maturity credits. We compare their structure to those generated by the IAS 39 and CECL accounting frameworks. The results indicate that the IFRS 9 and CECL frameworks generate efficient credit portfolios whose structure penalizes riskier‐rated credits. In turn, the riskier efficient credit portfolios under the IAS 39 framework concentrate entirely on speculative‐grade credits. This pattern is also encountered in efficient credit portfolios constructed based on credits with different maturities, namely 5 and 15 years. Moreover, the longer the maturity of the credits that enter into the composition of the efficient portfolios, the more the speculative‐grade credits tend to be penalized.