Hierarchical Classification of Financial Transactions Through Context-Fusion of Transformer-based Embeddings and Taxonomy-aware Attention Layer

Antonio J. G. Busson, Rafael Rocha, Rennan Gaio, Rafael Miceli, Ivan Pereira +12 more
12/12/2023
cs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

This work proposes the Two-headed DragoNet, a Transformer-based model for hierarchical multi-label classification of financial transactions. Our model is based on a stack of Transformers encoder layers that generate contextual embeddings from two short textual descriptors (merchant name and business activity), followed by a Context Fusion layer and two output heads that classify transactions according to a hierarchical two-level taxonomy (macro and micro categories). Finally, our proposed Taxonomy-aware Attention Layer corrects predictions that break categorical hierarchy rules defined in the given taxonomy. Our proposal outperforms classical machine learning methods in experiments of macro-category classification by achieving an F1-score of 93\% on a card dataset and 95% on a current account dataset.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{busson2023hierarchical,
  title  = {Hierarchical Classification of Financial Transactions Through Context-Fusion of Transformer-based Embeddings and Taxonomy-aware Attention Layer},
  author = {Antonio J. G. Busson and Rafael Rocha and Rennan Gaio and Rafael Miceli and Ivan Pereira and Daniel de S. Moraes and Sérgio Colcher and Alvaro Veiga and Bruno Rizzi and Francisco Evangelista and Leandro Santos and Fellipe Marques and Marcos Rabaioli and Diego Feldberg and Debora Mattos and João Pasqua and Diogo Dias},
  year   = {2023},
  eprint = {2312.07730},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.07730v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.07730.svg)](https://codeofpaper.com/paper/2312.07730)

Discussion