← Research

Can ML predict the solution value for a difficult combinatorial problem?

Constantine Goulimis, Gast\'on Simone

We look at whether machine learning can predict the final objective function value of a difficult combinatorial optimisation problem from the input. Our context is the pattern reduction problem, one industrially important but difficult aspect of the cutting stock problem. Machine learning appears to have higher prediction accuracy than a na\"ive model, reducing mean absolute percentage error (MAPE) from 12.0% to 8.7%.

PDF ↗

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace