Models / group-data-ai

group-data-ai/transaction-narrative-ner

Transaction Narrative Entity Extractor

ConfidentialMinimal riskGroup ReuseLanguage AITransformersBilingual1.3.0
132 684K/30d 77

Entity F1 (micro)

0.912

Counterparty name F1

0.938

Purpose classification accuracy

0.864

Batch throughput

9,000 rows/s

About this model

Pulls structured entities out of free-text payment narratives on DuitNow, IBG and FPX transfers: merchant or counterparty name, payment purpose (rent, salary, loan repayment, gift, investment), reference numbers and platform names. Handles English, Bahasa Malaysia and typical abbreviations ("sewa", "gaji", "byr").

Intended use

Feature enrichment for fraud, mule and AML models, spend categorisation, and investigator search. Output enriches transactions; it does not decide anything on its own.

Training data lineage

Token-classification model fine-tuned from a multilingual encoder on 120,000 narratives sampled from casa-transactions in BigQuery and labelled in-house by Financial Crime analysts. Trained, evaluated and registered in Vertex AI; batch inference runs nightly in BigQuery through a remote model.

Limitations & bias notes

Narratives under three characters or made only of emojis carry no signal. Purpose labels are indicative; "gift" and "loan" are often confused in informal transfers between family members.

Evaluation metrics

Entity F1 (micro)0.912
Counterparty name F10.938
Purpose classification accuracy0.864
Batch throughput9,000 rows/s
#ner#payments#duitnow#ibg#fpx#bahasa-malaysia#enrichment

Try it

Live sandbox

Feedback

Owning business unit

DAGroup Data & AI
Updated
2026-07-06
Latest version
1.3.0
Licence
Group Reuse
Access
Open to all BUs