Two-Stage Network DEA with Undesirable Outputs
DEA-NETWORK (Two-Stage Network DEA with Undesirable Outputs) is a dea multi-criteria decision-making (MCDM) method introduced by Fukuyama, H. Weber, W. L. in 2010. It turns a decision matrix of alternatives scored on multiple criteria into a structured, reproducible result.
Read the full method
Sign in with a free account to read this section.
When to use it
DEA-NETWORK extends black-box DEA by modelling internal production structure with intermediate products. Stage 1 produces intermediate goods (e.g. deposits); Stage 2 converts them to final outputs plus undesirable by-products (e.g. nonperforming loans). Weak disposability handles bad outputs. Link constraints ensure intermediate product consistency between stages.
Strengths & limitations
- Follows a transparent, reproducible computational procedure that can be audited step by step.
- Handles multiple criteria of differing scales and units within a single decision matrix.
- Assumes full compensation — a strong score on one criterion can offset a weak score on another.
Sources
- Fukuyama, H., Weber, W. L. (2010). A slacks-based inefficiency measure for a two-stage system with bad outputs. Omega DOI: 10.1016/j.omega.2009.10.006 ↗
How to cite this page
ScholarGate. (2026, June 2). Two-Stage Network DEA with Undesirable Outputs. ScholarGate. https://scholargate.app/en/decision-making/dea-network