model-index:
- name: Sociovestix/lenu_US-NY
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: lenu
type: Sociovestix/lenu
config: US-NY
split: test
revision: fbe0b4b5b8d6950c10f5710f2c987728635a4afe
metrics:
- type: f1
value: 0.9506172839506173
name: f1
- type: f1
value: 0.5638405396306392
name: f1 macro
args:
average: macro
widget:
- text: 949-959 SOUTHERN BLVD LLC
- text: Lumico Life Insurance Company of New York
- text: BNP PARIBAS ASSET MANAGEMENT USA HOLDINGS, INC.
- text: QB ASSOCIATES, L.P.
- text: THE LOTOS CLUB
- text: LOMBARD & GELIBETER LLP
- text: Walden Savings Bank
- text: Adirondack Bank
- text: The North Country Savings Bank
LENU - Legal Entity Name Understanding for US New York
A finbert model fine-tuned on US New York legal entity names (jurisdiction US-NY) from the Global Legal Entity Identifier (LEI) System with the goal to detect Entity Legal Form (ELF) Codes.
in collaboration with
Model Description
The model has been created as part of a collaboration of the Global Legal Entity Identifier Foundation (GLEIF) and Sociovestix Labs with the goal to explore how Machine Learning can support in detecting the ELF Code solely based on an entity's legal name and legal jurisdiction. See also the open source python library lenu, which supports in this task.
The model has been trained on the dataset lenu, with a focus on US New York legal entities and ELF Codes within the Jurisdiction "US-NY".
- Developed by: GLEIF and Sociovestix Labs
- License: Creative Commons (CC0) license
- Finetuned from model [optional]: yiyanghkust/finbert-pretrain
- Resources for more information: Press Release
Uses
An entity's legal form is a crucial component when verifying and screening organizational identity. The wide variety of entity legal forms that exist within and between jurisdictions, however, has made it difficult for large organizations to capture legal form as structured data. The Jurisdiction specific models of lenu, trained on entities from GLEIF’s Legal Entity Identifier (LEI) database of over two million records, will allow banks, investment firms, corporations, governments, and other large organizations to retrospectively analyze their master data, extract the legal form from the unstructured text of the legal name and uniformly apply an ELF code to each entity type, according to the ISO 20275 standard.
Licensing Information
This model, which is trained on LEI data, is available under Creative Commons (CC0) license. See gleif.org/en/about/open-data.
Recommendations
Users should always consider the score of the suggested ELF Codes. For low score values it may be necessary to manually review the affected entities.