SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection

TL;DR

This paper introduces SAE-FiRE, a framework that uses sparse autoencoders and feature selection to improve earnings surprise predictions from complex financial documents, reducing noise and enhancing model robustness.

Contribution

SAE-FiRE is a novel approach combining sparse autoencoders with statistical feature selection to extract key information from large financial texts for better prediction accuracy.

Findings

SAE-FiRE outperforms baseline models on three financial datasets.

The framework effectively reduces noise and redundancy in financial text representations.

Sparse autoencoders improve interpretability of features for earnings surprise prediction.

Abstract

Predicting earnings surprises from financial documents, such as earnings conference calls, regulatory filings, and financial news, has become increasingly important in financial economics. However, these financial documents present significant analytical challenges, typically containing over 5,000 words with substantial redundancy and industry-specific terminology that creates obstacles for language models. In this work, we propose the SAE-FiRE (Sparse Autoencoder for Financial Representation Enhancement) framework to address these limitations by extracting key information while eliminating redundancy. SAE-FiRE employs Sparse Autoencoders (SAEs) to decompose dense neural representations from large language models into interpretable sparse components, then applies statistical feature selection methods, including ANOVA F-tests and tree-based importance scoring, to identify the top-k most discriminative dimensions for classification. By systematically filtering out noise that might otherwise lead to overfitting, we enable more robust and generalizable predictions. Experimental results across three financial datasets demonstrate that SAE-FiRE significantly outperforms baseline approaches.