Collected molecules will appear here. Add from search or explore.
An implementation of an adaptive model selection algorithm (IBEA-MS) for offline data-driven multi-objective evolutionary optimization, designed to select the best surrogate models when real-world function evaluations are expensive or unavailable.
Defensibility
stars
3
forks
1
IBEA-MS is a specialized academic implementation representing a specific research paper in the field of Surrogate-Assisted Evolutionary Computation (SAEC). With only 3 stars and 1 fork over a 4-year period, it has zero market traction and serves exclusively as a code artifact for peer review or academic reproduction. The defensibility is near zero because it is a standalone algorithm implementation without a supporting library ecosystem or user base. While the niche (offline data-driven optimization) is resistant to frontier labs (OpenAI/Google) due to its focus on traditional engineering simulations rather than generative AI, the project is easily displaced by more comprehensive optimization frameworks like PyGMO, DEAP, or Optuna. The 'displacement horizon' is rated at 6 months because newer academic techniques likely already supersede this approach, and the lack of updates suggests the repository is no longer maintained.
TECH STACK
INTEGRATION
reference_implementation
READINESS