## Pilot Service: AI-Powered Proxy Advisor for Shareholder Proposals
What is This Service?
This pilot platform generates proxy voting recommendations using insights derived from my co-authored paper: Beyond Bias: AI as a Proxy Advisor. It leverages an AI model with its domain knowledge of proxy voting, offering shareholders, governance professionals, and researchers a complementary and experimental approach to traditional proxy advisory recommendations.
Why This Matters
Transparency: Each recommendation is generated using the standardized prompt structure outlined in the paper. The versions for the AI model and other tools are all disclosed in this website.
Innovation: Leverages the capabilities of AI (Language Model) to interpret the context of shareholder proposals with relevant domain knowledge (Proxy Voting).
Accessibility: Provides an academic lens on ESG issues for anyone with an interest in corporate governance and shareholder activism.
How It Works
Proposal Input: Enter a shareholder proposal of your choice, with your supporting arguments for it, via Google Form here.
Example - Proposal:
Shareholders request that [COMPANY] issue a sustainability report describing the company's environmental, social and governance (ESG) performance and goals, including greenhouse gas (GHG) reduction goals. The report should be available on the company website by May 20XX, prepared at reasonable cost, omitting proprietary information.
Example - Supporting arguments:
We believe tracking and reporting ESG business practices makes a company more responsive to a transforming global business environment characterized by finite natural resources, changing legislation, and heightened public expectations for corporate accountability. Reporting also helps companies better integrate and gain strategic value from existing sustainability efforts, identify gaps and opportunities in products and processes, develop company-wide communications, publicize innovative practices, and receive feedback.
Support for and the practice of sustainability reporting continues to gain momentum:
• In 20YY, [COMPANY] found that of 4,100 global companies seventy-one percent had ESG reports.
• The United Nations Principles for Responsible Investment has more than 1,260 signatories with over $45 trillion of assets under management. These members seek ESG information from companies to be able to analyze fully the risks and opportunities associated with existing and potential investments.
• The [COMPANY] (formerly [COMPANY]), representing 767 institutional investors globally with approximately $92 trillion in assets, calls for company disclosure on greenhouse gas emissions and climate change management programs. Over two thirds of the S&P 500 now report to [COMPANY].
[COMPANY] has minimal disclosure on how it manages ESG issues. By contrast, the company's peers including [COMPANY], [COMPANY], [COMPANY], and [COMPANY] have much more comprehensive sustainability reporting, providing goals, identifying areas of focus, and data on their progress. Public disclosure of this information allows investors to learn more about how management is addressing near and long-term risks (e.g. operational, reputational, and regulatory) and opportunities.
Reporting on the company's impact on climate change is particularly crucial as it is one of the most financially significant environmental issues currently facing investors. We believe no firm is immune to the prospect of future carbon regulations or the physical impacts of climate change.
In addition, investors have an interest in understanding how the company manages labor and human rights issues. Working conditions in [COMPANY]'s warehouses have drawn scrutiny and labor and human rights issues in corporate supply chains are important for any company involved with retail sales.
Research Matching: An internal system identifies all the relevant input components for the AI model's final prompt. For instance, the system retrieves and processes historical opposition statements used against similar proposals. These statements are hand-collected from SEC proxy filings and prepared for the referenced academic paper.
Recommendation Generation: The AI model produces a recommendation (e.g., For / Against).
Given the limited time and resources available:
Proposals are accepted throughout the week, and all submission from the previous week are processed on Monday. Reports will be sent to the email address provided in the Google Form.
For each weekly batch, only the most recent proposal submitted by the same requester will be considered.
Current Model & Tools:
AI Model: Llama 3.3 70B Instruct model (commit 6f6073b423013f6a7d4d9f39144961bfbfbc386b) with bfloat16 for the model precision
Tools: Transformers library (Hugging Face) version 4.55.0, with PyTorch 2.5.1 + CUDA 12.4 in Python 3.12.7
Differences between the Referenced Academic Paper and This Service
The Paper: Reproducibility of results is essential for academic evidence. Therefore, I deliberately restrict the AI model from deviating, requiring it to select the output token with the highest probability within its domain knowledge.
This Service: In contrast, this pilot service is intended as a practical and exploratory experiment. Here, I allow the model greater flexibility and creativity, which means that even for the same proposal, the generated recommendations may vary.
Disclaimer for This Pilot Service
This is an early-stage pilot service, and I welcome constructive feedback. choonsiklee79@gmail.com
This service is operated solely with my own time, effort, and resources. Processing times may vary depending on the availability.
The reports generated by this service do not constitute tax, legal, insurance, or investment advice, nor do they represent a recommendation, offer, or solicitation to buy or sell any product, vehicle, service, or instrument. By using this service, you acknowledge that you have read and understood this disclaimer and agree to release me from any liability related to its use.
Version History
2025-09-03: Pilot Service Started