TEKNO Method: Total Evaluation based on Knowledge-driven Normalized Optimization for Multi-Criteria Decision Making

Yuri Rahmanto (Universitas Teknokrat Indonesia)
Ryan Randy Suryono (Universitas Teknokrat Indonesia)
Dedi Darwis (Universitas Teknokrat Indonesia)
Abhishek R. Mehta (Parul University)
Auliya Rahman Isnain (Universitas Teknokrat Indonesia)

Journal of Decision Support Systems and Multi-Criteria Decision Making (JODESMA)
Vol. 1 No. 2 (2027): March 2027

Multi-criteria decision making (MCDM) methods play an important role in supporting decisions involving multiple criteria with different characteristics and levels of importance. However, differences in normalization procedures, criterion treatment, and aggregation mechanisms can lead to variations in the resulting preference structures. This study proposes a new MCDM method, namely total evaluation based on knowledge-driven normalized optimization (TEKNO), which integrates normalization, relative evaluation, criterion weighting, optimization-based normalization, and total evaluation into a unified decision-making framework. The proposed method is designed to transform heterogeneous decision information into comparable evaluation values while preserving the relative contribution of each criterion. The applicability of TEKNO is evaluated through two decision-making case studies involving new store location selection and leasing customer selection. The evaluation framework includes ranking analysis, comparison with established MCDM methods, Spearman rank correlation analysis, and sensitivity analysis under variations in criterion weights. The results show that TEKNO achieves a Spearman rank correlation coefficient of 1.0000 for the new store location case and 0.9964 for the leasing customer selection case, indicating very strong agreement with the reference rankings. In addition, the ranking remains unchanged across the tested sensitivity scenarios, demonstrating the stability of TEKNO under variations in criterion weights. These findings indicate that TEKNO provides a transparent, systematic, and stable alternative for MCDM applications for practical decision support where reliable ranking, methodological transparency, and robustness across alternative evaluation conditions are required. Nevertheless, broader validation using diverse datasets, decision domains, weighting schemes, and statistical evaluation techniques is required to further establish its generalizability and comparative performance.