FiNCAT: Financial Numeral Claim Analysis Tool

TL;DR

FiNCAT is an automated tool that uses transformer-based embeddings and logistic regression to identify whether financial numerals in documents are in-claim or out-of-claim, aiding investors in decision-making.

Contribution

The paper introduces FiNCAT, a novel tool combining BERT embeddings and logistic regression for financial numeral claim detection, trained on the FinNum-3 dataset.

Findings

Achieved a Macro F1 score of 0.8223 on validation data.

Open-sourced tool available at GitHub.

Effective in distinguishing in-claim from out-of-claim numerals.

Abstract

While making investment decisions by reading financial documents, investors need to differentiate between in-claim and outof-claim numerals. In this paper, we present a tool which does it automatically. It extracts context embeddings of the numerals using one of the transformer based pre-trained language model called BERT. After this, it uses a Logistic Regression based model to detect whether the numerals is in-claim or out-of-claim. We use FinNum-3 (English) dataset to train our model. After conducting rigorous experiments we achieve a Macro F1 score of 0.8223 on the validation set. We have open-sourced this tool and it can be accessed from https://github.com/sohomghosh/FiNCAT_Financial_Numeral_Claim_Analysis_Tool