Confident recommendations
A patent-pending gating layer on your sequential backbone — compose learned structure when support is sufficient; defer to baseline when it is not.
Move your cursor — confidence crystallizes near the probe.
Lattice sits on top of the backbone you already ship. Binary ON/OFF controls whether an auxiliary scoring path is blended in — not whether items are filtered from a list.
LSTM, transformer, SASRec — any sequential ranker you already train and serve. Lattice never replaces it.
When in-support confidence is below threshold, the gate stays OFF. Metrics and rankings match baseline exactly — auditable, not down-weighted.
When ON, archetypes fit in the backbone's embedding space and fusion activates. Ungated mode reaches higher pooled HR; gating trades peak benchmark for control.
MovieLens primary eval: 30 paired seeds, full-catalog ranking, identical test rows per seed. Lifts are vs each backbone alone — not literature SOTA comparisons. Benchmark access for independent verification: LorianBannis@banlys.com.
| Backbone | Dataset | Gated lift (HR@10) | Ungated lift | Seeds | Note |
|---|---|---|---|---|---|
| LSTM | MovieLens | +31.7% | +58.7% | 30 | Primary estimand |
| Transformer | MovieLens | +13.3% | +20.9% | 30 | Backbone-native archetypes |
| SASRec | MovieLens | +17.0% | +26.9% | 30 | Contextual baseline + Lattice |
| LSTM | Amazon Electronics | +124.0% | +211.6% | 15 | Supporting — high variance |
Primary headline: LSTM +31.7% gated (+58.7% ungated). Transformer +13.3% and SASRec +17.0% use backbone-native archetypes. Amazon +124.0% is supporting evidence only (small test set, high variance). We do not claim gating maximizes in-distribution accuracy — we claim auditable ON/OFF with zero harm when OFF.
Always-on fusion scores higher on pooled benchmarks in our ablation (+58.7% vs +31.7% gated on MovieLens). We do not sell peak benchmark mode. We sell an auditable ON/OFF switch: when off, predictions match your backbone; when on, you capture full fusion gain on supported rows.
Lattice gates whether an auxiliary scoring path is composed with your backbone — not whether individual items are filtered from a list. When the gate is OFF, ranked output matches the backbone exactly; when ON, it matches always-on fusion on the same session.
Mock rankings for education only — composition policy (OFF ≡ backbone, ON ≡ fusion), not item filtering. Does not expose production confidence formulas or training pipelines.
Eval protocol and pilot KPIs focus on coverage, lift when ON, and zero harm when OFF. Hosted API access follows pilot validation — not self-serve yet.
A Banly's product · Patent pending · RecSys 2026 under review · LorianBannis@banlys.com