What type of study is this?

This is a Quantitative Study study (also classified as: Experimental Study).

September 30, 2025Open Access

Predicting Internal Control Deficiencies from Investor Online Interaction Texts

Key Points

The early-fusion model significantly improves prediction accuracy for internal control deficiencies, enhancing decision-making.
Incorporating text data yields an Average Precision improvement of 18.3% and a ROC-AUC enhancement of 5.1%, indicating its predictive value.
This approach combines investor interaction texts with financial ratios within a unified deep learning framework for better prediction.
The findings support the use of textual information in regulatory early-warning systems, improving corporate assessments.

Abstract

This study adopts a text-based perspective to transform Q further adopting hierarchical text fusion yields cumulative improvements of 18.3% and 5.1% over the baseline. The findings document the incremental predictive value of text data for internal control deficiencies and provide effective tools for regulatory early-warning, audit sampling, and corporate self-assessment, with important theoretical and practical implications.

Ask AI

Helpful

Bookmark

View Full Paper