Layout
This commit is contained in:
Yijia-Xiao
210
index.html
210
index.html
@@ -190,29 +190,17 @@
|
||||
<div class="content has-text-justified">
|
||||
<p>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.</p>
|
||||
|
||||
<div class="columns is-multiline">
|
||||
<div class="column is-one-quarter">
|
||||
<div class="columns">
|
||||
<div class="column">
|
||||
<figure class="image">
|
||||
<img src="./static/images/Analyst.png" alt="TradingAgents Analyst Team">
|
||||
<figcaption class="has-text-centered"><strong>Figure 2:</strong> TradingAgents Analyst Team</figcaption>
|
||||
</figure>
|
||||
</div>
|
||||
<div class="column is-one-quarter">
|
||||
<div class="column">
|
||||
<figure class="image">
|
||||
<img src="./static/images/Researcher.png" alt="TradingAgents Researcher Team">
|
||||
<figcaption class="has-text-centered"><strong>Figure 3:</strong> TradingAgents Researcher Team: Bullish Perspectives and Bearish Perspectives</figcaption>
|
||||
</figure>
|
||||
</div>
|
||||
<div class="column is-one-quarter">
|
||||
<figure class="image">
|
||||
<img src="./static/images/Trader.png" alt="TradingAgents Trader Decision-Making Process">
|
||||
<figcaption class="has-text-centered"><strong>Figure 4:</strong> TradingAgents Trader Decision-Making Process</figcaption>
|
||||
</figure>
|
||||
</div>
|
||||
<div class="column is-one-quarter">
|
||||
<figure class="image">
|
||||
<img src="./static/images/RiskMGMT.png" alt="TradingAgents Risk Management Team and Fund Manager Approval Workflow">
|
||||
<figcaption class="has-text-centered"><strong>Figure 5:</strong> TradingAgents Risk Management Team and Fund Manager Approval Workflow</figcaption>
|
||||
<figcaption class="has-text-centered"><strong>Figure 3:</strong> TradingAgents Researcher Team</figcaption>
|
||||
</figure>
|
||||
</div>
|
||||
</div>
|
||||
@@ -243,6 +231,21 @@
|
||||
<div class="content has-text-justified">
|
||||
<p>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.</p>
|
||||
|
||||
<div class="columns">
|
||||
<div class="column">
|
||||
<figure class="image">
|
||||
<img src="./static/images/Trader.png" alt="TradingAgents Trader Decision-Making Process">
|
||||
<figcaption class="has-text-centered"><strong>Figure 4:</strong> TradingAgents Trader Decision-Making Process</figcaption>
|
||||
</figure>
|
||||
</div>
|
||||
<div class="column">
|
||||
<figure class="image">
|
||||
<img src="./static/images/RiskMGMT.png" alt="TradingAgents Risk Management Team and Fund Manager Approval Workflow">
|
||||
<figcaption class="has-text-centered"><strong>Figure 5:</strong> TradingAgents Risk Management Team and Fund Manager Approval Workflow</figcaption>
|
||||
</figure>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<ul>
|
||||
<li>Evaluating recommendations and insights from analysts and researchers.</li>
|
||||
<li>Deciding on the timing and size of trades to maximize trading returns.</li>
|
||||
@@ -366,106 +369,104 @@
|
||||
<table class="table is-striped is-fullwidth is-centered">
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Metric</th>
|
||||
<th>Buy and Hold</th>
|
||||
<th>MACD</th>
|
||||
<th>KDJ & RSI</th>
|
||||
<th>ZMR</th>
|
||||
<th>SMA</th>
|
||||
<th>TradingAgents</th>
|
||||
<th>Categories</th>
|
||||
<th>Models</th>
|
||||
<th colspan="4">AAPL</th>
|
||||
<th></th>
|
||||
<th colspan="4">GOOGL</th>
|
||||
<th></th>
|
||||
<th colspan="4">AMZN</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<th></th>
|
||||
<th></th>
|
||||
<th>CR%↑</th>
|
||||
<th>ARR%↑</th>
|
||||
<th>SR↑</th>
|
||||
<th>MDD%↓</th>
|
||||
<th></th>
|
||||
<th>CR%↑</th>
|
||||
<th>ARR%↑</th>
|
||||
<th>SR↑</th>
|
||||
<th>MDD%↓</th>
|
||||
<th></th>
|
||||
<th>CR%↑</th>
|
||||
<th>ARR%↑</th>
|
||||
<th>SR↑</th>
|
||||
<th>MDD%↓</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><strong>Cumulative Return (CR%)</strong></td>
|
||||
<td>-5.23</td>
|
||||
<td>-1.49</td>
|
||||
<td>2.05</td>
|
||||
<td>0.57</td>
|
||||
<td>-3.2</td>
|
||||
<td><strong style="color:green;">26.62</strong></td>
|
||||
<td>Market</td>
|
||||
<td>B&H</td>
|
||||
<td>-5.23</td><td>-5.09</td><td>-1.29</td><td>11.90</td>
|
||||
<td></td>
|
||||
<td>7.78</td><td>8.09</td><td>1.35</td><td>13.04</td>
|
||||
<td></td>
|
||||
<td>17.1</td><td>17.6</td><td>3.53</td><td>3.80</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><strong>Annualized Return (AR%)</strong></td>
|
||||
<td>-5.09</td>
|
||||
<td>-1.48</td>
|
||||
<td>2.07</td>
|
||||
<td>0.57</td>
|
||||
<td>-2.97</td>
|
||||
<td><strong style="color:green;">30.50</strong></td>
|
||||
<td rowspan="4">Rule-based</td>
|
||||
<td>MACD</td>
|
||||
<td>-1.49</td><td>-1.48</td><td>-0.81</td><td>4.53</td>
|
||||
<td></td>
|
||||
<td>6.20</td><td>6.26</td><td>2.31</td><td>1.22</td>
|
||||
<td></td>
|
||||
<td>-</td><td>-</td><td>-</td><td>-</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><strong>Sharpe Ratio (SR)</strong></td>
|
||||
<td>-1.29</td>
|
||||
<td>-0.81</td>
|
||||
<td>1.64</td>
|
||||
<td>0.17</td>
|
||||
<td>-1.72</td>
|
||||
<td><strong style="color:green;">8.21</strong></td>
|
||||
<td>KDJ&RSI</td>
|
||||
<td>2.05</td><td>2.07</td><td>1.64</td><td>1.09</td>
|
||||
<td></td>
|
||||
<td>0.4</td><td>0.4</td><td>0.02</td><td>1.58</td>
|
||||
<td></td>
|
||||
<td>-0.77</td><td>-0.76</td><td>-2.25</td><td>1.08</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><strong>Maximum Drawdown (MDD%)</strong></td>
|
||||
<td>11.90</td>
|
||||
<td>4.53</td>
|
||||
<td>1.09</td>
|
||||
<td>0.86</td>
|
||||
<td>3.67</td>
|
||||
<td>0.91</td>
|
||||
<td>ZMR</td>
|
||||
<td>0.57</td><td>0.57</td><td>0.17</td><td>0.86</td>
|
||||
<td></td>
|
||||
<td>-0.58</td><td>0.58</td><td>2.12</td><td>2.34</td>
|
||||
<td></td>
|
||||
<td>-0.77</td><td>-0.77</td><td>-2.45</td><td>0.82</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>SMA</td>
|
||||
<td>-3.2</td><td>-2.97</td><td>-1.72</td><td>3.67</td>
|
||||
<td></td>
|
||||
<td>6.23</td><td>6.43</td><td>2.12</td><td>2.34</td>
|
||||
<td></td>
|
||||
<td>11.01</td><td>11.6</td><td>2.22</td><td>3.97</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="1">Ours</td>
|
||||
<td><strong>TradingAgents</strong></td>
|
||||
<td><strong style="color:green;">26.62</strong></td><td><strong style="color:green;">30.5</strong></td><td><strong style="color:green;">8.21</strong></td><td>0.91</td>
|
||||
<td></td>
|
||||
<td><strong style="color:green;">24.36</strong></td><td><strong style="color:green;">27.58</strong></td><td><strong style="color:green;">6.39</strong></td><td>1.69</td>
|
||||
<td></td>
|
||||
<td><strong style="color:green;">23.21</strong></td><td><strong style="color:green;">24.90</strong></td><td><strong style="color:green;">5.60</strong></td><td>2.11</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td colspan="2">Improvement(%)</td>
|
||||
<td>24.57</td><td>28.43</td><td>6.57</td><td>-</td>
|
||||
<td></td>
|
||||
<td>16.58</td><td>19.49</td><td>4.26</td><td>-</td>
|
||||
<td></td>
|
||||
<td>6.10</td><td>7.30</td><td>2.07</td><td>-</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<p class="has-text-centered"><strong>Table 1:</strong> Performance comparison of TradingAgents against baseline models using four evaluation metrics.</p>
|
||||
<p class="has-text-centered"><strong>Table 1:</strong> TradingAgents (<strong>AIS</strong>): 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.</p>
|
||||
|
||||
<h4 class="title is-5">Cumulative Return (CR)</h4>
|
||||
<p>The cumulative return measures the total return generated over the simulation period. It is calculated as:</p>
|
||||
<p>
|
||||
<strong>CR</strong> = ((V<sub>end</sub> - V<sub>start</sub>) / V<sub>start</sub>) × 100%
|
||||
</p>
|
||||
<p>where V<sub>end</sub> is the portfolio value at the end of the simulation, and V<sub>start</sub> is the initial portfolio value.</p>
|
||||
|
||||
<h4 class="title is-5">Annualized Return (AR)</h4>
|
||||
<p>The annualized return normalizes the cumulative return over the number of years:</p>
|
||||
<p>
|
||||
<strong>AR</strong> = (((V<sub>end</sub> / V<sub>start</sub>)^(1/N)) - 1) × 100%
|
||||
</p>
|
||||
<p>where N is the number of years in the simulation.</p>
|
||||
|
||||
<h4 class="title is-5">Sharpe Ratio (SR)</h4>
|
||||
<p>The Sharpe ratio measures risk-adjusted return by comparing a portfolio's excess return over the risk-free rate to its volatility:</p>
|
||||
<p>
|
||||
<strong>SR</strong> = (R̄ - R<sub>f</sub>) / σ
|
||||
</p>
|
||||
<p>where R̄ is the average portfolio return, R<sub>f</sub> is the risk-free rate (e.g., yield of 3-month Treasury bills), and σ is the standard deviation of the portfolio returns.</p>
|
||||
|
||||
<h4 class="title is-5">Maximum Drawdown (MDD)</h4>
|
||||
<p>Maximum drawdown measures the largest peak-to-trough decline in the portfolio value:</p>
|
||||
<p>
|
||||
<strong>MDD</strong> = max<sub>t ∈ [0, T]</sub> ((Peak<sub>t</sub> - Trough<sub>t</sub>) / Peak<sub>t</sub>) × 100%
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section class="section">
|
||||
<div class="container is-max-desktop">
|
||||
<div class="columns is-centered">
|
||||
<div class="column is-full-width">
|
||||
<h2 class="title is-3">Results and Analysis</h2>
|
||||
<div class="content has-text-justified">
|
||||
<h3 class="title is-4">Performance Comparison</h3>
|
||||
|
||||
<h4 class="title is-5">Cumulative and Annual Returns</h4>
|
||||
<p>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. <strong>TradingAgents</strong> 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, <strong>TradingAgents</strong> excelled even under these adverse conditions, achieving returns exceeding 26% within less than three months.</p>
|
||||
|
||||
<h4 class="title is-5">Sharpe Ratio</h4>
|
||||
<h3 class="title is-4">Sharpe Ratio</h3>
|
||||
<p>The Sharpe Ratio performance highlights <strong>TradingAgents</strong>' 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 <strong>TradingAgents</strong>' 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, <strong>TradingAgents</strong> 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.</p>
|
||||
|
||||
<h4 class="title is-5">Maximum Drawdown</h4>
|
||||
<h3 class="title is-4">Maximum Drawdown</h3>
|
||||
<p>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 <strong>TradingAgents</strong>' strength as a balanced approach. Despite higher returns being typically associated with higher risks, <strong>TradingAgents</strong> 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 <strong>TradingAgents</strong>' capability to strike a robust balance between maximizing returns and managing risk effectively.</p>
|
||||
|
||||
<h4 class="title is-5">Explainability</h4>
|
||||
<h3 class="title is-4">Explainability</h3>
|
||||
<p>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.</p>
|
||||
|
||||
<p>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 <strong>TradingAgents</strong> 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.</p>
|
||||
@@ -475,19 +476,6 @@
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section class="section">
|
||||
<div class="container is-max-desktop">
|
||||
<div class="columns is-centered">
|
||||
<div class="column is-full-width">
|
||||
<h2 class="title is-3">Conclusion</h2>
|
||||
<div class="content has-text-justified">
|
||||
<p>In this paper, we introduced <strong>TradingAgents</strong>, 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, <strong>TradingAgents</strong> 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 <strong>TradingAgents</strong> 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.</p>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<footer class="footer">
|
||||
<div class="container">
|
||||
<div class="content has-text-centered">
|
||||
|
||||
Reference in New Issue
Block a user