This page is published in English.
Ranking
STOCHASTIC-UTA - Stochastic UTilités Additives (preference-disaggregation under uncertainty)
Preference disaggregation with LP utility fitting + Monte Carlo acceptability analysis
Stavrou, D. I., Ventikos, N. P., Tsoukalas, V. D.2018doi:10.1007/978-3-319-62338-2_8 ↗
Overview
STOCHASTIC-UTA fits additive utility functions to a DM-supplied reference ranking via LP, then samples uncertain inputs N times (Monte Carlo) to derive acceptability indices. In deterministic mode (N=1), the score is the global utility u(A_i); in stochastic mode it is the holistic acceptability a_i.
- Output
- utility or acceptability, higher is better
- Data
- Crisp, reference ranking required
- Weights
- Derived internally, no weight source needed
- Size
- 3+ alternatives, 3-10 criteria works best
- Used for
- Maritime risk assessment, energy/CHP technology selection, health system evaluation, R&D project selection, supplier selection under uncertainty, logistics process improvement
Fits when / Look elsewhere when
Fits when
- •Recovers weights implicitly from the DM ranking (no separate weight elicitation)
- •Explicit utility functions per criterion (interpretable; supports sensitivity analysis)
- •Native uncertainty handling via Monte Carlo + SMAA acceptability indices
- •Quantified robustness indices (b_i^r, a_i, central weights, confidence factor)
Look elsewhere when
- •No reference ranking available - use SMAA or direct weighting
- •Criteria are strongly interacting - use ANP or Choquet integral
- •Need a closed-form weight vector explicitly - use AHP / BWM
Assumptions to verify
- DM is able and willing to supply a reference ranking of all (or a representative subset of) alternatives
- Preferences are additively separable across criteria
- Piecewise-linear marginal utilities are an adequate approximation
- For Monte Carlo mode: per-cell probability distributions are well-calibrated
Limitations
- •Computationally heavy in Monte Carlo mode (N LP solves)
- •Requires DM to commit to a reference ranking (cognitively demanding)
- •LP may admit multiple optimal vertices - solver-dependent tie-breaking
- •Piecewise-linear assumption may be too restrictive for highly non-linear preferences
Edge cases and pitfalls
- •LP infeasible (δ* too large): σ+, σ- become non-zero; solver still returns optimal but Z > 0 - surface as warning.
- •Multiple LP optima: HiGHS deterministic tie-breaking → fixture reproducible. For research-grade use, average vertices (UTA stability analysis).
- •All alternatives tied in DM ranking: LP becomes trivial; method falls back to equal-weight average.
- •Cost criterion: negate column upstream (F1) before LP.
Reference ranking missing one or more alternatives - LP becomes under-constrained.
Choosing δ* too large relative to the natural utility gaps - LP becomes infeasible (forces σ+ + σ- > 0).
Forgetting to negate cost criteria upstream - direction-handling explicit.
Works with
How to cite
Stavrou, D. I.; Ventikos, N. P.; Tsoukalas, V. D. (2018). Robust Evaluation of Risks in Ship-to-Ship Transfer Operations: Application of the STOCHASTIC UTA Multicriteria Decision Support Method. In Lee, P. T. W. & Yang, Z. (Eds.), Multi-criteria Decision Making in Maritime Studies and Logistics (pp. 161-185). Springer.. https://doi.org/10.1007/978-3-319-62338-2_8
System ID, as it appears in reports and the API
STOCHASTIC-UTA