Market Microstructure Research·2026

Prediction Market Execution Lab

Testing executable edge in Polymarket BTC short-horizon markets.

Execution Lab
Active Analysis
Theoretical Edge
100%
Frictions
65%
Executable
42%

Why It Matters

This project separates apparent market edge from executable edge, which is closer to how real trading and execution research should be evaluated.

Context

Short-horizon prediction markets may show apparent pricing edge, but apparent edge is not the same as executable edge.

What I Built

I built a public research lab with sample data, notebooks, reports, dashboard, execution diagnostics, calibration analysis, ML filtering, and risk simulation.

Research Workflow

  • Market data sample
  • Signal construction
  • Execution funnel
  • Fill diagnostics
  • Calibration analysis
  • Risk simulation
  • Public-safe reporting

Key Highlights

  • Separates theoretical pricing edge from executable edge.
  • Includes public-safe sample data, research reports, notebooks, and a live dashboard.
  • Analyzes execution funnel, probability calibration, ML filtering, and risk simulation.
  • Explicitly avoids profitability claims and private execution-sensitive details.

What This Demonstrates

  • Market microstructure reasoning
  • Data analysis and research communication
  • Separating theoretical signal from executable outcome
  • Building public-safe research artifacts without exposing sensitive execution data

Representative Artifacts

Execution Funnel

Visualizing the degradation of theoretical edge into executable edge due to frictions.

Edge Degradation Funnel
Theoretical Signal100%
Post-Spread Frictions65%
Executable Reality42%

Calibration Simulation

Modeling probability accuracy and risk exposure across varied market conditions.

Calibration Sim
Kelly Fraction0.15
Brier Score0.142
Implied vs Realized

Research Dashboard

Abstract view of market depth, liquidity metrics, and execution diagnostics.

Research Abstract
Liquidity Depth
$42.5k
Slippage Est.
-1.2%

Tech Stack

PythonStreamlitPandasNumPy

This project is presented as a public research and portfolio artifact. It does not represent financial advice, trading advice, or a claim of trading profitability.