Paper: arXiv 2510.10526

Authors: Wo Long, Wenxin Zeng, Xiaoyu Zhang, Ziyao Zhou

Abstract

This research develops a sentiment-driven quantitative trading system that leverages a large language model, FinGPT, for sentiment analysis, and explores a novel method for signal integration using a reinforcement learning algorithm, Twin Delayed Deep Deterministic Policy Gradient (TD3). We compare the performance of strategies that integrate sentiment and technical signals using both a conventional rule-based approach and a reinforcement learning framework. The results suggest that sentiment signals generated by FinGPT offer value when combined with traditional technical indicators, and that reinforcement learning algorithm presents a promising approach for effectively integrating heterogeneous signals in dynamic trading environments.

Complexity vs Empirical Score

  • Math Complexity: 8.0/10
  • Empirical Rigor: 8.5/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced mathematics, including TD3 (a sophisticated deep reinforcement learning algorithm) and quantitative finance concepts, while also demonstrating high empirical rigor through detailed data sourcing (Thomson Reuters, CRSP, Bloomberg), a backtest-ready framework, robustness checks for look-ahead bias, and performance evaluation against benchmarks.

Research Flowchart

  flowchart TD
  Start["Research Goal: Integrate Sentiment & Technical Signals for Trading"] --> Data["Inputs: Financial Data & News Sentiment via FinGPT"]
  Data --> Method["Methodology: Rule-Based vs. RL TD3"]
  Method --> Comp["Computation: Signal Processing & Portfolio Optimization"]
  Comp --> Out["Outcome: RL Approach Outperforms in Volatile Markets"]
  Out --> End["Key Finding: Sentiment Adds Value & RL is Promising"]

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 sentiment-driven quantitative trading system using FinGPT for sentiment analysis and integrates these signals with technical indicators via a reinforcement learning algorithm (TD3).

Source sentence
This research develops a sentiment-driven quantitative trading system that leverages a large language model, FinGPT, for sentiment analysis, and explores a novel method for signal integration using a reinforcement learning algorithm, Twin Delayed Deep Deterministic Policy Gradient (TD3).

Assumes 4

  • Orders are executed at the same day’s closing price (trades filled at the closing auction). execution
    Source sentence
    Orders are executed at the same day’s closing price (i.e., trades filled at the closing auction (≈4 p.m. ET). )
  • Zero transaction costs are assumed for the rule‑based strategy by default. execution
    Source sentence
    We assume zero transaction costs for the rule-based strategy by default.
  • Long‑short strategy starts with an initial investment of zero. execution
    Source sentence
    Long-Short Strategy with initial investment of 0.
  • News articles released after 4 p.m. are dropped to ensure same‑day trading viability. data
    Source sentence
    We also dropped news articles released after 4 p.m. on each trading day to ensure the viability of sentiment signals for same-day trading decisions.

Data

Backtest sample: 2018 – 2025 · S&P 500 stocks · equities · daily

  • Thomson Reuters news articles · Thomson Reuters text-news commercial
    2018-2025 · 44 S&P 500 stocks with most active news coverage
    Source sentence
    The news data are sourced from Thomson Reuters, covering the period from 2018 to 2025, and include the 44 S&P 500 stocks selected based on the most active level of news coverage.
  • CRSP daily stock data · CRSP market-prices commercial
    2018-2025 · 44 S&P 500 stocks
    Source sentence
    The historical price and volume data for the selected universe are daily-level data sourced from CRSP and Bloomberg, spanning also from 2018 to 2025.
  • Bloomberg market data (prices, volume, VWAP) · Bloomberg market-prices commercial
    2018-2025 · 44 S&P 500 stocks
    Source sentence
    The technical data include primarily open and close prices, trading volume (measured as number of shares traded per day) obtained from CRSP, and VWAP sourced from Bloomberg.

Recognised sources: Bloomberg CRSP Refinitiv / LSEG (Datastream, Eikon, Tick History)

Costs

Modeled Costs are part of the reported headline results.

A flat transaction cost of 5 basis points per trade is applied in the main backtests; a robustness check also uses 10 bps.

Source sentence
we also evaluate the strategy’s performance under a transaction cost of 5 basis points per trade.

Finds 4

Reported performance (Rule-based long-short sentiment‑technical combined strategy): Sharpe 0.75 · annual return 13.8% · max drawdown 37.3%

  • Applying a 5 bps transaction cost reduces the rule‑based strategy’s annualised return from 13.84% to 3.66% (sentiment weight = 0), a drop of more than 10 % absolute. performance
    Source sentence
    Comparing the two full sample performance tables, we observe a clear deterioration in annualized return once a 5bps transaction cost is applied. For example, under sentiment weight = 0, the annualized return drops from 13.84% to 3.66%.
  • Sentiment signals generated by FinGPT add incremental value beyond traditional technical indicators, as indicated by positive performance when combined. performance
    Source sentence
    The results suggest that sentiment signals generated by FinGPT offer value when combined with traditional technical indicators.
  • Factor decomposition of the TD3 excess returns shows a high market beta (βmktrf = 0.91) and insignificant idiosyncratic alpha after transaction costs. statistical
    Source sentence
    ... yields R2 = 0.65 and an insignificant intercept (p = 0.93), indicating that the market beta explains most of the variation.
  • Both rule‑based and RL‑driven strategies exhibit high turnover; the RL strategy’s 52 % annual turnover still delivers superior risk‑adjusted returns despite transaction costs. performance
    Source sentence
    the RL agent delivers a Sharpe ratio of 1.38 despite a 52 % annual turnover even after imposing a conservatively high-level transaction cost of 10bps.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 31 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.