Random Forest ensembles are a strong baseline for tabular prediction tasks, but their reliance on hundreds of deep trees often results in high inference latency and memory demands, limiting deployment in latency-sensitive or resource-constrained environments. We introduce DiNo (Distance with Nodes) and RanBu (Random Bushes), two shallow-forest methods that convert a small set of depth-limited trees into efficient, distance-weighted predictors. DiNo measures cophenetic distances via the most recent common ancestor of observation pairs, while RanBu applies kernel smoothing to Breiman's classical proximity measure. Both approaches operate entirely after forest training: no additional trees are grown, and tuning of the single bandwidth parameter $h$ requires only lightweight matrix-vector operations. Across three synthetic benchmarks and 25 public datasets, RanBu matches or exceeds the accuracy of full-depth random forests-particularly in high-noise settings-while reducing training plus inference time by up to 95\%. DiNo achieves the best bias-variance trade-off in low-noise regimes at a modest computational cost. Both methods extend directly to quantile regression, maintaining accuracy with substantial speed gains. The implementation is available as an open-source R/C++ package at https://github.com/tiagomendonca/dirf. We focus on structured tabular random samples (i.i.d.), leaving extensions to other modalities for future work.

A phylogenetic tree shows the evolutionary relationships among species. Internal nodes of the tree represent speciation events and leaf nodes correspond to species. A goal of phylogenetics is to combine such trees into larger trees, called supertrees, whilst respecting the relationships in the original trees. A rooted tree exhibits an ultrametric property; that is, for any three leaves of the tree it must be that one pair has a deeper most recent common ancestor than the other pairs, or that all three have the same most recent common ancestor. This inspires a constraint programming encoding for rooted trees. We present an efficient constraint that enforces the ultrametric property over a symmetric array of constrained integer variables, with the inevitable property that the lower bounds of any three variables are mutually supportive. We show that this allows an efficient constraint-based solution to the supertree construction problem. We demonstrate that the versatility of constraint programming can be exploited to allow solutions to variants of the supertree construction problem.