A Novel Technique for Criteria Weighting in Multi-Criteria Decision-Making: Tanimoto Contrast Approach (TCA)

This study introduces the Tanimoto Contrast Approach (TCA), a novel objective method for determining criterion weights in Multi-Criteria Decision-Making (MCDM) problems. Built on the internal–external dispersion logic of the CRITIC method, TCA replaces Pearson correlation with Tanimoto similarity to capture both linear and non-linear relationships, enabling a more comprehensive evaluation of inter-criterion contrasts and similarities. The method was tested using the 2024 Global Innovation Index data from selected seven countries. Sensitivity analysis revealed that TCA maintains ranking stability under varying conditions, while comparative analysis showed strong correlation with ENTROPY, SVP, and MEREC methods, confirming its reliability and credibility. In addition, simulation analysis based on ten different decision matrix scenarios demonstrated that TCA produces high average variance and consistent, homogeneous weight distributions evidence of its robustness and stability. TCA’s advantages include distribution free applicability, insensitivity to zero or negative values, scale independence, and effectiveness with large datasets. Moreover, its comparative performance against widely used objective weighting methods such as ENTROPY, CRITIC, SD, SVP, MEREC, and LOPCOW has been thoroughly discussed. In conclusion, TCA offers contrast-based, decision-maker-independent weighting framework that generates meaningful, balanced, and sensitive results. Its integration into MCDM applications provides a valuable contribution to the advancement of objective weighting techniques.