The aim of this study is to adapt a well-known interactive and multi-criteria decision-making method, TODIM, to the portfolio allocation process. The proposed method is applied to empirical US equity data by employing variance, correlation and returns calculated on different observation periods as decision criteria. A total of 440 different configurations are applied to analyze the impact of several parameters in TODIM. Based on the results for the test period, outperforming TODIM configurations are elected. In the validation period, it is empirically demonstrated that portfolios based on outperforming TODIM configurations yield significantly better results than equally weighted portfolios (1/N) and insignificantly inferior results than the minimum variance portfolio (MVP) in terms of the Sharpe ratio. However, TODIM may still be a better choice than MVP for investors sensitive to concentration risk and turnover costs. (C) 2019 Elsevier Ltd. All rights reserved.