MeanyDeany

Research infrastructure for systematic trading

Check the trading ideabefore risking capital.

I build systems that turn raw market data into verified datasets, reproducible experiments, and auditable research results.

The goal is not to make a model look profitable. The goal is to determine whether a research claim can be trusted, repeated, and rejected before it is allowed anywhere near a trading decision.

See the flagship systemView all research

Plain-English answer

So what does this actually do?

It answers one question: can a systematic trading idea be trusted before money is put at risk?

  1. 01What is it?

    Research and validation infrastructure for systematic trading.

    It is the layer that checks data, experiment identity, reproducibility, and evidence quality before a trading strategy is trusted.

  2. 02What does it do?

    It turns raw market data into evidence that can be audited.

    The system verifies datasets, preserves provenance, reproduces experiments, and keeps research results from being silently rewritten.

  3. 03Does it make money?

    Not currently.

    There is no live strategy, fund, signal service, or trading revenue. The current product is the research foundation for future systematic strategies.

How it works

Research infrastructure. Not signal theatre.

Market data01

Know what the model actually saw.

Public market data is captured, verified, normalized, and assigned a deterministic identity before it becomes experiment input.

Follow the data lifecycle
Research experiments02

Make results reproducible.

Datasets, code, parameters, environments, and results are bound to exact identities so the same claim can be reconstructed and challenged.

Inspect the architecture
Decision control03

Keep evidence away from the order button.

A strong model result remains research evidence. It cannot silently become entry permission, strategy approval, position sizing, or execution authority.

Read the hard boundaries

What it could become

The foundation for multi-asset systematic research.

The current system does not produce returns. Its value is creating a reliable base for future proprietary strategies, quantitative research tools, and institutional research workflows without pretending that infrastructure is already a profitable product.

Research chain

  1. 01Raw market data
  2. 02Verified dataset
  3. 03Reproducible experiment
  4. 04Auditable result
  5. 05Controlled decision
Open the full system

No black box.No silent repair.No fake profitability claim.

Read the methodologyContact

Latest build

Show the increments, not just the ambition.

The public record separates completed engineering, supported claims, and the limits that remain.

Open the build logRead the claims ledger
Prospective evidence operations01

23 Jul 2026

A separate baseline evidence pipeline now runs prospectively.

The BTC research system now schedules immutable hourly-RV inputs, two simple baseline forecast states, and one-hour forward outcomes as a separate three-job research pipeline.

Prospective evidence scheduling is operational infrastructure, not model selection, strategy approval, or execution authority.

Operational health02

23 Jul 2026

Baseline evidence health is measured without grading the forecasts.

A manual read-only diagnostic now validates complete input, state, and outcome stores, cross-layer lineage, scheduler status, cron identity, freshness, and bounded maturity coverage.

Health and operational maturity measure evidence flow and integrity. They do not assess forecast usefulness or authorize comparison, paper trading, or live trading.

Model-free baselines03

22 Jul 2026

Two simple volatility baselines gained immutable forecast and outcome evidence.

Naive last-hour realized variance and a 24-hour rolling mean remain outside the model registry while receiving separate immutable input, forecast-state, and forward-outcome evidence.

Simple baselines are research comparators under accumulation. Their presence is not ranking, promotion, strategy approval, or trading permission.