The Short Version

The Decay Lab is a quantitative trading research platform. I find strategies that professional traders and academics have documented, optimize them for small-account deployment, and only put real capital behind them after they survive a full validation pipeline — backtesting, parameter sweeps, Monte Carlo simulation, walk-forward testing, and paper trading on real market data. Every strategy earns its way to live trading. None of them skip the line.

The Founder

I'm a physicist by training — B.S. in Physics, B.A. in Natural & Applied Sciences, and a Master's in Physics, with doctoral research at Jefferson Lab on deep inelastic scattering experiments funded by the Department of Energy.

In particle physics, your code is your eyes. You can't watch a parton get knocked out of a proton and recombine into a shower of particles in 10^-23 seconds. You build mathematical models, write the analysis code, and that's how you see what happened. I got very good at one thing: extracting real signals from noisy data and knowing exactly how confident to be in the result.

He wasn't wrong. Jim Simons, a mathematician and theoretical physicist, founded Renaissance Technologies and its Medallion Fund — widely considered the most successful hedge fund in history. David Shaw, a computational scientist, founded D.E. Shaw & Co. Emanuel Derman went from particle physics at Columbia to becoming head of quantitative strategies at Goldman Sachs. The pattern is consistent: people trained to find real signals in overwhelming noise tend to do well when the noise is market data instead of particle collisions.

I built this platform because the problem is the same. Extract a real signal from noisy data, model the uncertainties honestly, and only act when the evidence meets a rigorous threshold. No gut feelings, no chart patterns, no "trust me" — just math and data.

The Process

It starts with research — academic papers, AQR white papers, industry publications, documented strategies from professional traders. Not looking for tips. Looking for edges with a structural reason to persist: strategies where someone has done the rigorous work and shown why the opportunity exists and why it shouldn't disappear.

From there I filter for what's actually reachable with a small account. Most institutional strategies require capital scale, infrastructure, or instruments retail traders can't access. What's left gets put through the pipeline: build the model, run backtests across years of real data, sweep parameters to find the optimum, then validate those results with walk-forward testing and Monte Carlo simulation. The goal isn't the best-looking backtest. It's the one where the edge is real and survives out-of-sample.

Anything that passes gets a paper bot — not a broker sandbox that fills at mid, but a real simulator running on live market data with realistic slippage and commissions. The paper results have to hold up before real capital goes in. The 1-DTE options strategy went through this entire pipeline before I deposited a dollar. The ORB futures bots are in the paper phase right now. They go live when the results are clean for a few consecutive weeks. That's the whole process. No shortcuts.

How I Work

• Hypothesis-driven, not curve-fit. Every strategy follows the scientific method. I never optimize to fit historical data and call it edge.
• Confidence intervals, not just win rates. A 70% win rate means nothing without knowing the uncertainty. I bootstrap thousands of resamples to compute the probability of genuine positive edge — the same standard you'd need to publish a physics result.
• Full cost transparency. Most signal services show mid-price fills and ignore fees. I model slippage using the 66% bid-ask spread model, compute commissions, and report net P&L after all expenses.
• Everything is verifiable. Every trade is published. Every backtest can be reproduced. No cherry-picking, no hidden losses, no black boxes.