Financial misstatement detection

Abstract

In this work, we examine the evaluation process for the task of detecting financial reports with a high risk of containing a misstatement. This task is often referred to, in the literature, as "misstatement detection in financial reports". We provide an extensive review of the related literature. We propose a new, realistic evaluation framework for the task which, unlike a large part of the previous work: (a) focuses on the misstatement class and its rarity, (b) considers the dimension of time when splitting data into training and test and (c) considers the fact that misstatements can take a long time to detect. Most importantly, we show that the evaluation process significantly affects system performance, and we analyze the performance of different models and feature types in the new realistic framework. CCS CONCEPTS• Information systems → Evaluation of retrieval results; Clustering and classification; • Computing methodologies → Ranking.

Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking

“…Intent detection is a particular case of text classification, and it is a vital component of task-oriented conversational systems in various domains, including finance. It reflects the complexity of actual commercial systems, which can be attributed to the partially overlapping intent categories, the need for fine-grained decisions, and the lack of comprehensive datasets in finance [5,25,26,48]. However, publicly available intent detection datasets are limited, and the existing ones fail to represent the complexity of real-world industrial systems [3,10].…”