Systematic research lab

Quant research that does not stop at the backtest.

AI Quant Forge analyses quantitative research, develops systematic strategies and tracks selected candidates in a live forward paper portfolio. We publish the reasoning, the limitations and what happens on unseen market data.

The portfolio trades in real time through a paper (simulated) brokerage account, so this is a live forward test rather than a backtest. Returns include the transaction costs, commissions and slippage applied by the portfolio’s execution model. No real money or client capital is involved, so the results remain hypothetical and may differ from results achievable in a live account. Everything here is research and education, not investment advice and not an offer to invest.

Research

Strategy case studies

Examples of systematic strategies developed and tested by AI Quant Forge. Each case study shows the hypothesis, implementation, results and limitations — not a recommendation or a list of our best-performing models.

New case studies are published here regularly.

Forward portfolio

Live results, kept apart from backtests

The track record we point to is the model portfolio, because it trades in real time: each result is recorded when it happens and cannot be touched up afterwards. Backtests appear on this site too, but only as separate research examples, because simulated history is far easier to make look good.

Forward model portfolio

LIVE FORWARD · PAPER

Trades in real time through a paper (simulated) brokerage account; each day's result is recorded at the close and never revised. Reported returns include the transaction costs, commissions and slippage applied by the portfolio's execution model. No real money or client capital is involved, so the results remain hypothetical.

Explore the full portfolio →

Backtested examples

HISTORICAL

Historical simulations of individual strategies, published as research examples. They stay separate from the live portfolio's record.

Methodology

How we research

Paper or hypothesis → implementation → audit and backtest → selection → forward testing → portfolio monitoring. The AI engine reads and structures the research, formalises the testable claims, helps write the code, runs the tests and audits, and records every result with its limitations. Weak candidates get cut along the way, and the ones that survive are managed together as one portfolio.

01 / GENERATE

Generate

An AI agent turns a research idea into a concrete strategy: trading rules, instruments, and code that runs.

02 / VALIDATE

Validate

The code is backtested on historical data, with transaction costs and risk limits applied. Implementation errors are corrected and the test is rerun. A failed hypothesis remains a failed result and may still be published.

03 / DEPLOY

Deploy

Candidates that survive validation may be selected for forward testing on the paper account.

04 / MONITOR

Monitor

Live results are recorded daily and compared against what the backtest promised. Portfolio changes follow the published rules and are timestamped, never revised after the fact.

Why we can publish all this. The core research platform remains proprietary, allowing us to publish its output openly while keeping access controlled.

Research principles

The rules the numbers live by

  • Every number reported as ours comes from stored system results.
  • Figures taken from a paper are attributed to the source.
  • Transaction costs and slippage are included and described.
  • Historical backtests are kept separate from forward results.
  • Negative findings can be published.
  • Methodology changes are timestamped.
  • Losing results receive the same scrutiny as winning ones.
  • Current positions and proprietary signals may remain undisclosed.
Subscribe

Follow what survives the research process.

Choose a daily Radar of newly identified papers or a weekly digest of the most interesting research.

About

About the lab

AI Quant Forge is an AI-native systematic research lab. Our research engine screens quantitative papers, extracts testable hypotheses and, where feasible, implements and backtests them. Human editors decide which analyses become editor-reviewed Paper Reviews, while selected strategies may progress to a live forward paper portfolio.

The core platform remains proprietary, but we selectively collaborate with research and institutional partners. For suitable projects, we can extend its data coverage, research tools and testing capabilities, or provide controlled access to structured hypotheses identified in new papers and parts of the research and backtesting pipeline.

Everything published on this site is free to read, and nothing here is investment advice.

Discuss a collaboration