Beyond the Numbers: Causal Effects of Financial Report Sentiment on Bank Profitability

Paper: arXiv 2602.17851

Authors: Krishna Neupane, Prem Sapkota, Ujjwal Prajapati

Abstract

This study establishes the causal effects of market sentiment on firm profitability, moving beyond traditional correlational analyses. It leverages a causal forest machine learning methodology to control for numerous confounding variables, enabling systematic analysis of heterogeneity and non-linearities often overlooked. A key innovation is the use of a pre-trained FinancialBERT to generate sentiment scores from quarterly reports, which are then treated as causal interventions impacting profitability dynamics like returns and volatilities. Utilizing a comprehensive dataset from NEPSE, NRB, and individual financial institutions, the research employs SHAP analysis to identify influential profit predictors. A two-pronged causal analysis further explores how sentiment’s impact is conditioned by Loan Portfolio/Asset Composition and Balance Sheet Strength/Leverage. Average Treatment Effect analyses, combined with SHAP insights, reveal statistically significant causal associations between certain balance sheet and expense management variables and profitability. This advanced causal machine learning framework significantly extends existing literature, providing a more robust understanding of how financial sentiment truly impacts firm performance.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 6.0/10 (capped from 7.5: no out-of-sample test; see penalty flags)
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: This paper presents a strong combination of modern causal machine learning (causal forests, AIPSS, SHAP) and natural language processing (FinancialBERT) to evaluate bank profitability in Nepal. It effectively bridges advanced empirical techniques with financial domain knowledge to move beyond simple correlations.

Research Flowchart

  flowchart TD
    A[Research Goal: Causal Effect of Financial Report Sentiment on Bank Profitability] --> B[Data Inputs: Financial Reports, NEPSE, NRB & Bank Data]
    B --> C[Sentiment Extraction: FinancialBERT processing Quarterly Reports]
    C --> D[Causal Machine Learning: Causal Forest Model & Confounder Control]
    D --> E[Model Interpretation: SHAP Analysis for Variable Importance]
    E --> F[Outcomes: Significant Causal Impact Conditioned by Balance Sheet & Portfolio Composition]