| --- |
| title: Transaction Encoder — LFM2.5 multi-head + Co-Pilot surfaces |
| emoji: 🪙 |
| colorFrom: gray |
| colorTo: indigo |
| sdk: gradio |
| sdk_version: 6.14.0 |
| app_file: app.py |
| pinned: false |
| --- |
| |
| # Transaction Encoder — One Backbone, Many Surfaces |
|
|
| Reference implementation of the multimodal-encoder recipe applied to |
| discrete-feature transaction sequences, demonstrating cross-surface |
| reuse on **the same customer history**. Same recipe as Liquid AI's |
| [LFM2.5-Audio](https://huggingface.co/LiquidAI/LFM2-Audio-1.5B) and |
| [LFM2.5-VL](https://huggingface.co/LiquidAI/LFM2-VL-1.6B): a small |
| per-modality encoder produces continuous embeddings, a projection |
| adapter maps them into the LFM2.5 text backbone's hidden space, and a |
| per-surface LoRA adapts the attention layers. |
|
|
| ## What this demo shows |
|
|
| Seven tabs over one shared LFM2.5-350M backbone: |
|
|
| - **Multi-Head Demo** — the original 4-task-head encoder demo. Live |
| inference on curated customer archetypes: fraud probability, |
| next-merchant prediction, amount-bucket prediction, MCC prediction. |
| - **Cold Start** — a brief self-supervised pretraining stage ("SSL") |
| catches ~5× more fraud at a fixed approval rate on a newly onboarded |
| merchant with almost no labels, while declining fewer good customers. |
| The same connector-pretraining stage LFM2.5-Audio and LFM2.5-VL use. |
| Synthetic-data demonstration with operating-point numbers + figure. |
| - **Why Liquid** — architectural pitch for the encoder-on-frozen-backbone |
| recipe. |
| - **Integration** — build-it-yourself guide. |
| - **Dispute Co-Pilot** — given a customer's transaction history + a |
| dispute complaint, classifies the dispute as likely / ambiguous / |
| unlikely friendly fraud, with per-transaction attribution. |
| - **Collections Co-Pilot** — given a delinquency context, predicts the |
| customer's likely response to each of 4 treatment options |
| (settlement / payment plan / soft-touch / no-offer). |
| - **Fraud Pattern Co-Pilot** — given an upstream-flagged transaction, |
| classifies the attack stage (5-way) AND the underlying type (4-way) |
| in two independent categorical outputs. |
|
|
| Each Co-Pilot surface ships its own slim checkpoint (~24 MB) alongside |
| the original multi-head checkpoint (~24 MB), but all four share the |
| LFM2.5-350M base weights — the demonstration that the backbone is the |
| product, and per-surface plumbing rides on top. |
|
|
| ## How it works |
|
|
| ``` |
| feature_ids (1, 64, 15) ──► TransactionEncoder ──► ProjectionAdapter |
| (per-feature embed, (LayerNorm + MLP, |
| concat, MLP + d_encoder → d_lfm) |
| surface markers) |
| │ |
| ▼ |
| [tx pseudo-tokens, SEP, context tokens] |
| │ |
| ▼ |
| LFM2.5-350M (frozen) + LoRA r=16 |
| │ |
| ▼ |
| ┌─────────────────────┬─────────────────────┐ |
| ▼ ▼ ▼ |
| Probability Head Attribution Head (LM head NOT trained; |
| (3 / K×3 / 5+4 (per-position reasoning rendered |
| per surface) binary) via Python template) |
| ``` |
|
|
| ## Scope |
|
|
| Reference implementation on synthetic data. Backbone is |
| [LFM2.5-350M](https://huggingface.co/LiquidAI/LFM2.5-350M-Base) (frozen) |
| plus ~6M trainable parameters per surface (encoder + projector + LoRA + |
| heads). Quality numbers reflect synthetic data — they should not be |
| cited as performance on real payment data. |
|
|
| ## Cast performance (held-out) |
|
|
| - Multi-Head V3 (step 4999): per-head accuracy reported on the test split. |
| - Dispute v7 (step 2000): 5/6 cast band-match, 6/6 attribution top-5 |
| - Collections v3 (step 4500): 5/6 cast band-match |
| - Fraud v1 (step 3000): 6/6 stage AND type at 1.00 confidence |
|
|
| ## Read more |
|
|
| - [LFM2 technical report (arXiv 2511.23404)](https://arxiv.org/abs/2511.23404) |
| - [LFM2 model weights on Hugging Face](https://huggingface.co/LiquidAI) |
|
|
