From 2e8a02e874c8b1421c9af47dd415efaa1d3faf2d Mon Sep 17 00:00:00 2001 From: Yijia-Xiao Date: Sat, 28 Dec 2024 12:35:29 +0800 Subject: [PATCH] Layout --- index.html | 210 +++++++++++++++++++++++++---------------------------- 1 file changed, 99 insertions(+), 111 deletions(-) diff --git a/index.html b/index.html index b9fa7eb..86bb145 100644 --- a/index.html +++ b/index.html @@ -190,29 +190,17 @@

The Analyst Team is composed of specialized agents responsible for gathering and analyzing various types of market data to inform trading decisions. Each agent focuses on a specific aspect of market analysis, bringing together a comprehensive view of the market's conditions.

-
-
+
+
TradingAgents Analyst Team
Figure 2: TradingAgents Analyst Team
-
+
TradingAgents Researcher Team -
Figure 3: TradingAgents Researcher Team: Bullish Perspectives and Bearish Perspectives
-
-
-
-
- TradingAgents Trader Decision-Making Process -
Figure 4: TradingAgents Trader Decision-Making Process
-
-
-
-
- TradingAgents Risk Management Team and Fund Manager Approval Workflow -
Figure 5: TradingAgents Risk Management Team and Fund Manager Approval Workflow
+
Figure 3: TradingAgents Researcher Team
@@ -243,6 +231,21 @@

Trader Agents are responsible for executing trading decisions based on the comprehensive analysis provided by the Analyst Team and the nuanced perspectives from the Researcher Team. They assess the synthesized information, considering both quantitative data and qualitative insights, to determine optimal trading actions.

+
+
+
+ TradingAgents Trader Decision-Making Process +
Figure 4: TradingAgents Trader Decision-Making Process
+
+
+
+
+ TradingAgents Risk Management Team and Fund Manager Approval Workflow +
Figure 5: TradingAgents Risk Management Team and Fund Manager Approval Workflow
+
+
+
+
  • Evaluating recommendations and insights from analysts and researchers.
  • Deciding on the timing and size of trades to maximize trading returns.
    • @@ -366,106 +369,104 @@ - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - + + + + + + + - - - - - - - + + + + + + + - - - - - - - + + + + + + - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
    MetricBuy and HoldMACDKDJ & RSIZMRSMATradingAgentsCategoriesModelsAAPLGOOGLAMZN
    CR%↑ARR%↑SR↑MDD%↓CR%↑ARR%↑SR↑MDD%↓CR%↑ARR%↑SR↑MDD%↓
    Cumulative Return (CR%)-5.23-1.492.050.57-3.226.62MarketB&H-5.23-5.09-1.2911.907.788.091.3513.0417.117.63.533.80
    Annualized Return (AR%)-5.09-1.482.070.57-2.9730.50Rule-basedMACD-1.49-1.48-0.814.536.206.262.311.22----
    Sharpe Ratio (SR)-1.29-0.811.640.17-1.728.21KDJ&RSI2.052.071.641.090.40.40.021.58-0.77-0.76-2.251.08
    Maximum Drawdown (MDD%)11.904.531.090.863.670.91ZMR0.570.570.170.86-0.580.582.122.34-0.77-0.77-2.450.82
    SMA-3.2-2.97-1.723.676.236.432.122.3411.0111.62.223.97
    OursTradingAgents26.6230.58.210.9124.3627.586.391.6923.2124.905.602.11
    Improvement(%)24.5728.436.57-16.5819.494.26-6.107.302.07-
    -

    Table 1: Performance comparison of TradingAgents against baseline models using four evaluation metrics.

    +

    Table 1: TradingAgents (AIS): Comparison of RNA Sequence (left), Modality Fusion (middle), and TradingAgents (right). Embedding base models are BERT, PubMedBERT, and OpenAI's GPT text-embedding-3-large.

    -

    Cumulative Return (CR)

    -

    The cumulative return measures the total return generated over the simulation period. It is calculated as:

    -

    - CR = ((Vend - Vstart) / Vstart) × 100% -

    -

    where Vend is the portfolio value at the end of the simulation, and Vstart is the initial portfolio value.

    - -

    Annualized Return (AR)

    -

    The annualized return normalizes the cumulative return over the number of years:

    -

    - AR = (((Vend / Vstart)^(1/N)) - 1) × 100% -

    -

    where N is the number of years in the simulation.

    - -

    Sharpe Ratio (SR)

    -

    The Sharpe ratio measures risk-adjusted return by comparing a portfolio's excess return over the risk-free rate to its volatility:

    -

    - SR = (R̄ - Rf) / σ -

    -

    where R̄ is the average portfolio return, Rf is the risk-free rate (e.g., yield of 3-month Treasury bills), and σ is the standard deviation of the portfolio returns.

    - -

    Maximum Drawdown (MDD)

    -

    Maximum drawdown measures the largest peak-to-trough decline in the portfolio value:

    -

    - MDD = maxt ∈ [0, T] ((Peakt - Trought) / Peakt) × 100% -

    -
-
-
-
- - -
-
-
-
-

Results and Analysis

-
-

Performance Comparison

- -

Cumulative and Annual Returns

-

Table 1 and Figures (a) and (b) highlight that our method significantly outperforms existing rule-based trading baselines, particularly in profitability, as measured by returns. TradingAgents achieves at least a 23.21% cumulative return and 24.90% annual return on the three sampled stocks, outperforming the best-performing baselines by a margin of at least 6.1%. Notably, on the AAPL stock—a particularly challenging case due to market volatility during the testing period—traditional methods struggled, as their patterns failed to generalize to this situation. In contrast, TradingAgents excelled even under these adverse conditions, achieving returns exceeding 26% within less than three months.

- -

Sharpe Ratio

+

Sharpe Ratio

The Sharpe Ratio performance highlights TradingAgents' exceptional ability to deliver superior risk-adjusted returns, consistently outperforming all baseline models across AAPL, GOOGL, and AMZN with Sharpe Ratios of at least 5.60—surpassing the next best models by a significant margin of at least 2.07 points. This result underscores TradingAgents' effectiveness in balancing returns against risk, a critical metric for sustainable and predictable investment growth. By excelling over market benchmarks like Buy-and-Hold and advanced strategies such as KDJRSI, SMA, MACD, and ZMR, TradingAgents demonstrates its adaptability and robustness in diverse market conditions. Its ability to maximize returns while maintaining controlled risk exposure establishes a solid foundation for multi-agent and debate-based automated trading algorithms.

-

Maximum Drawdown

+

Maximum Drawdown

While rule-based baselines demonstrated superior performance in controlling risk, as reflected by their maximum drawdown scores, they fell short in capturing high returns. This trade-off between risk and reward underscores TradingAgents' strength as a balanced approach. Despite higher returns being typically associated with higher risks, TradingAgents maintained a relatively low maximum drawdown compared to many baselines. Its effective risk-control mechanisms, facilitated by the debates among risk-control agents, ensured that the maximum drawdown remained within a manageable limit, not exceeding 2%. This demonstrates TradingAgents' capability to strike a robust balance between maximizing returns and managing risk effectively.

-

Explainability

+

Explainability

A significant drawback of current deep learning methods for trading is their dense and complex architectures, which often render the decisions made by trading agents indecipherable to humans. This challenge, rooted in the broader issue of AI explainability, is particularly critical for trading agents, as they operate in real-world financial markets, often involving substantial sums of money where incorrect decisions can lead to severe consequences and losses.

In contrast, an LLM-based agentic framework for trading offers a transformative advantage: its operations and decisions are communicated in natural language, making them highly interpretable to humans. To illustrate this, we provide the full trading log of TradingAgents for a single day in the Appendix, showcasing its use of the ReAct-style prompting framework. Each decision made by the agents is accompanied by detailed reasoning, tool usage, and thought processes, enabling traders to easily understand and debug the system. This transparency empowers traders to fine-tune and adjust the framework to account for factors influencing decisions, offering a significant edge in explainability over traditional deep-learning trading algorithms.

@@ -475,19 +476,6 @@
-
-
-
-
-

Conclusion

-
-

In this paper, we introduced TradingAgents, an LLM-agent-powered stock trading framework that simulates a realistic trading firm environment with multiple specialized agents engaging in agentic debates and conversations. Leveraging the capabilities of LLMs to process and analyze diverse data sources, the framework enables informed trading decisions while utilizing multi-agent interactions to enhance performance through comprehensive reasoning and debate before acting. By integrating agents with distinct roles and risk profiles, along with a reflective agent and a dedicated risk management team, TradingAgents significantly improves trading outcomes and risk management compared to baseline models. Additionally, the collaborative nature of these agents ensures adaptability to varying market conditions. Extensive experiments demonstrate that TradingAgents outperforms traditional trading strategies and baselines in cumulative return, Sharpe ratio, and other critical metrics. Future work will focus on deploying the framework in a live trading environment, expanding agent roles, and incorporating real-time data processing to enhance performance further.

-
-
-
-
-
-