Rebound

Navigation

Explore

Choose a platform module or vertical, then jump straight to the corresponding page.

Company / Research foundation

We did the math
so your regulators don't have to.

Rebound sits on peer-reviewed research at the intersection of chaos theory, ensemble model selection, and decision engineering. The numbers below are proven results, not marketing estimates.

27.2%

reduction in grid instability penalties — wind power scheduling, 24-hour horizon.

31.7%

improvement in traffic-flow optimization — adaptive signal timing, 48-hour window.

18–34%

decision-utility lift across domains when horizon-constrained selection replaces RMSE selection.

λ ↦ k*

Lyapunov exponents reliably predict the forecast horizon at which accuracy diverges from decision utility.

Selected publications

Our papers & preprints

Horizon-Constrained Rashomon Sets for Chaotic Systems
Rebound Research · Working paper · 2025
[PDF]
Lyapunov-Weighted Model Selection under Predictive Multiplicity
Rebound Research · Under review · ICML 2026
[PDF]
Architectural Diversity and Reliability Decay in Ensemble AI
Rebound Research · Preprint · arXiv
[PDF]
Glossary

The vocabulary we standardize on.

Rashomon Set

The set of ML models that perform equally well (within tolerance) on a given validation dataset. Named after the Kurosawa film — multiple equally valid accounts of the same event.

Lyapunov exponent (λ)

A measure of exponential divergence of nearby trajectories in a dynamical system. Positive λ indicates chaos; larger λ indicates faster divergence.

Predictability horizon (k*)

The lead time beyond which an AI's prediction is statistically indistinguishable from random noise, given the current λ.

Predictive multiplicity

The phenomenon where multiple equally-accurate models make systematically different predictions on individual cases or future steps.

Decision utility

A domain-specific measure of the real-world value of an AI recommendation — distinct from statistical accuracy. For trading, risk-adjusted return; for grid ops, avoided balancing penalty.

Horizon-Constrained Rashomon Set

The subset of the Rashomon set that maintains reliable decision utility up to a specific forecast horizon k.

Work with our research team.

We co-author with design-partner customers on domain-specific results.

Start a conversation