Public investment research · Est. 2026

Can a committee of expert investors be simulated from primary sources?

Five investors rebuilt from their own writing run a real $10,000 portfolio against the Dow 30, in public.

Committee against the Dow

A real $10,000 account runs the committee's decisions. Every week the portfolio value is recorded against the Dow Jones Industrial Average from a common baseline; the analytics below reconstruct the account day by day from the project's own position records and free daily market data. This is one line of evidence, not the verdict on the project.

Loading analytics…

Account value

Allocation

Monthly returns %

Drawdown % below prior peak, live account

Rolling 30-day volatility current weights over trailing year, annualized %

Daily return distribution

Holding correlations daily returns, trailing year

−1 diversifying0+1 moves together

Filled positions click a column to sort

These are the account's actual filled positions, reconciled weekly against the brokerage's own export. The committee's conviction-weighted target weights are published separately; fills drift from targets with market movement between rebalances.

Weekly public record vs close-based reconstruction

The weekly record captures the account intraday; the engine values are end-of-day closes, so small deltas between the two are expected and shown, not hidden.

Coverage

Engine notes

The committee's target weights.

These are the committee's target weights: conviction-weighted from the latest screen, not the live brokerage balances. Buys are sized in proportion to conviction; the committee is long-only by construction. The actual filled positions (shares and market value) are tracked in the analytics above and reconciled against these targets.

Holdings will appear here once the first weekly portfolio is published.

What this project actually tests.

Primary
Question 01

Can distinct expert reasoning be simulated from primary sources?

Each investor is reconstructed only from their own writing: letters, books, memos, and reports. The question is whether a language model, grounded that way, reproduces a coherent and recognizable investment mind, and whether five of them can genuinely deliberate rather than simply average.

Secondary
Question 02

Does the simulated committee form a viable strategy?

If the simulation holds, does the committee's decision-making translate into investment decisions worth acting on? A real $10,000 portfolio, benchmarked against the Dow 30 it selects from, supplies the evidence, measured over time rather than declared in advance.

Five investors, five frameworks, grounded in their own words.

Chosen to span complementary and often conflicting philosophies, so that genuine disagreement carries information. Each is simulated exclusively from primary sources.

One evaluation, four phases.

The engine separates independent judgment from social influence, so the committee deliberates rather than merely polls.

Enrich

Live market data on the security is gathered and shaped into a structured investment brief.

Blind vote

Each investor issues an independent verdict and conviction, without seeing any colleague's view.

Deliberate

Members see each other's positions and respond to the sharpest disagreement, revising if warranted.

Synthesize

A secretary writes the official committee statement: the verdict, the carrying argument, and the dissent.

Open by default.

The method, the source, and the findings are published so the work can be read, checked, and challenged.

Methodology Paper

Simulating a Committee of Expert Investors

The full apparatus: libraries, the committee engine, retrieval grounding, the cost economics, and the portfolio process. Published before results, against a fixed method.

Read the paper →
Source & Methodology

The code behind the committee

The engine, retrieval pipeline, and tooling, published as a public GitHub repository for transparency and scrutiny. No API keys and no copyrighted corpora are included; the method is documented so it can be read and checked.

View the code on GitHub →
Ongoing Analysis

Is the strategy valid?

Future write-ups examining fidelity of the simulation, the committee's structural tilts, and whether performance holds up to scrutiny over time.

Forthcoming