Paper: arXiv 2507.09739

Authors: Haojie Liu, Zihan Lin, Randall R. Rojas

Abstract

This study integrates real-time sentiment analysis from financial news, GPT-2 and FinBERT, with technical indicators and time-series models like ARIMA and ETS to optimize S&P 500 trading strategies. By merging sentiment data with momentum and trend-based metrics, including a benchmark buy-and-hold and sentiment-based approach, is evaluated through assets values and returns. Results show that combining sentiment-driven insights with traditional models improves trading performance, offering a more dynamic approach to stock trading that adapts to market changes in volatile environments.

Complexity vs Empirical Score

  • Math Complexity: 4.5/10
  • Empirical Rigor: 6.0/10 (capped from 7.5: transaction costs not modelled; see penalty flags)
  • Quadrant: Street Traders — empirical and applied, lower math complexity (effective empirical rigor capped from 7.5)

Why this score: The paper uses established time-series models (ARIMA, ETS) and basic technical indicators, but lacks advanced mathematical derivations, focusing instead on practical implementation. Empirical rigor is high due to real-time data integration, benchmarking against buy-and-hold, and evaluation of trading performance on S&P 500.

Research Flowchart

  flowchart TD
  A["Research Goal: Enhance S&P 500 Trading Performance"] --> B["Data Acquisition & Sentiment Analysis"]
  B --> C{"Data Processing"}
  C --> D["Computational Models & Integration"]
  D --> E["Backtesting & Benchmarking"]
  E --> F["Key Findings & Outcomes"]
  
  B --> B1["Financial News Data"]
  B --> B2["GPT-2 & FinBERT Models"]
  
  C --> C1["Technical Indicators"]
  C --> C2["Real-time Sentiment Scores"]
  
  D --> D1["ARIMA & ETS Time-Series Models"]
  D --> D2["Momentum/Trend Metrics"]
  
  E --> E1["Buy-and-Hold Benchmark"]
  E --> E2["Sentiment-Based Strategy"]
  
  F --> F1["Improved Trading Performance"]
  F --> F2["Dynamic Market Adaptation"]
  F --> F3["Superior Volatility Handling"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes a hybrid trading strategy that integrates real-time sentiment analysis from financial news using GPT-2 and FinBERT with technical indicators and time‑series models (ARIMA, ETS) to improve S&P 500 trading performance.

Source sentence
This study integrates real-time sentiment analysis from financial news, GPT-2 and FinBERT, with technical indicators and time-series models like ARIMA and ETS to optimize S&P 500 trading strategies.

Assumes 2

  • The simulation assumes zero transaction costs and slippage. execution
    Source sentence
    For simplicity, this simulation assumes zero transaction costs and slippage.
  • Sentiment models treat each headline equally, ignoring article length, author credibility, or source‑specific biases. model
    Source sentence
    Our sentiment models treat each headline equally and do not account for article length, author credibility, or source-specific biases.

Data

Backtest sample: S&P 500 · equities · daily

  • Financial news articles · Wall Street Journal, Barron, Benzinga, MarketWatch, Dow Jone text-news public
    Source sentence
    In this study, we utilize two key datasets: financial news articles collected from sources such as the Wall Street Journal (WSJ), Barron, Benzinga, MarketWatch, and Dow Jones, along with daily stock prices for the S&P 500 index.
  • S&P 500 daily price data · Yahoo Finance market-prices public
    August 08, 2019 to August 07, 2024 · S&P 500 index
    Source sentence
    We downloaded this data from Yahoo Finance, capturing daily prices from August 08, 2019 to August 07, 2024.

Recognised sources: Yahoo Finance

Costs

Not modeled A trading or execution result is reported without costs.

Source sentence
For simplicity, this simulation assumes zero transaction costs and slippage.

Finds 3

Reported performance (Sentiment-driven trading strategy combining GPT-2 (or FinBERT) with VW MACD): total return 5.8%

  • The hybrid strategy outperformed the baseline buy‑and‑hold, delivering a top‑performing return of 5.77%. performance
    Source sentence
    The top-performing version delivered a 5.77% return, demonstrating the value that can be had.
  • GPT‑2 combined with VW MACD and ARIMA achieved the highest overall return of 4.39% for Dow Jones data. performance
    Source sentence
    GPT-2 achieves the highest return overall, 4.39%, when paired with VW MACD ARIMA for Dow Jones, surpassing FinBERT’s 0.52%.
  • Combining sentiment‑driven insights with traditional models improves trading performance. performance
    Source sentence
    Results show that combining sentiment-driven insights with traditional models improves trading performance.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 17 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.