MANA-Net: Mitigating Aggregated Sentiment Homogenization with News Weighting for Enhanced Market Prediction

ArXiv ID: 2409.05698 “View on arXiv”

Authors: Unknown

Abstract

It is widely acknowledged that extracting market sentiments from news data benefits market predictions. However, existing methods of using financial sentiments remain simplistic, relying on equal-weight and static aggregation to manage sentiments from multiple news items. This leads to a critical issue termed ``Aggregated Sentiment Homogenization’’, which has been explored through our analysis of a large financial news dataset from industry practice. This phenomenon occurs when aggregating numerous sentiments, causing representations to converge towards the mean values of sentiment distributions and thereby smoothing out unique and important information. Consequently, the aggregated sentiment representations lose much predictive value of news data. To address this problem, we introduce the Market Attention-weighted News Aggregation Network (MANA-Net), a novel method that leverages a dynamic market-news attention mechanism to aggregate news sentiments for market prediction. MANA-Net learns the relevance of news sentiments to price changes and assigns varying weights to individual news items. By integrating the news aggregation step into the networks for market prediction, MANA-Net allows for trainable sentiment representations that are optimized directly for prediction. We evaluate MANA-Net using the S&P 500 and NASDAQ 100 indices, along with financial news spanning from 2003 to 2018. Experimental results demonstrate that MANA-Net outperforms various recent market prediction methods, enhancing Profit & Loss by 1.1% and the daily Sharpe ratio by 0.252.

Keywords: Market Attention-weighted News Aggregation Network (MANA-Net), Financial Sentiment Analysis, Dynamic Aggregation, Deep Learning, Market Prediction, Equities

Complexity vs Empirical Score

  • Math Complexity: 5.5/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Holy Grail
  • Why: The paper employs advanced deep learning techniques like attention mechanisms and neural network architectures, indicating moderate-to-high math complexity, and it is empirically rigorous with a large 15-year dataset, backtested on S&P 500 and NASDAQ 100 indices, reporting specific PnL and Sharpe ratio improvements.
  flowchart TD
    A["Research Goal:<br>Enhance Market Prediction<br>using Financial News"] --> B["Identify Problem:<br>Aggregated Sentiment Homogenization"]
    B --> C["Data:<br>S&P 500/NASDAQ 100 & News 2003-2018"]
    C --> D["Method: MANA-Net<br>Dynamic Market-News Attention"]
    D --> E["Process: Learn Relevance &<br>Assign Varying Weights"]
    E --> F["Outcome: Trainable<br>Sentiment Representations"]
    F --> G["Key Findings:<br>+1.1% P&L & +0.252 Sharpe Ratio"]