Add Signal Workflow

Step-by-step process for adding a new predictive signal. Follow measurement-before-modeling: define what you're predicting, log it, measure baseline, then build.

Step 1: Define the Signal

Before writing code, answer:

What does it predict? (price direction, fill probability, adverse selection, volatility)
At what horizon? (100ms, 1s, 10s, 60s)
What is the prediction target metric? (Brier Score for binary, IR for continuous)
What is the baseline? (naive predictor, e.g., always predict 50% for binary)

Step 2: Implement the Estimator

Create a new file in src/market_maker/estimator/:

// src/market_maker/estimator/my_signal.rs

pub struct MySignalEstimator {
    // State for online estimation
    // Use EWMA, rolling windows, or Bayesian updates
}

impl MySignalEstimator {
    pub fn new(config: MySignalConfig) -> Self { ... }

    /// Update with new market data. Called on every relevant event.
    pub fn update(&mut self, data: &MarketData) { ... }

    /// Get current signal value, normalized to a useful range.
    /// Document units in the return type or name.
    pub fn signal_value(&self) -> f64 { ... }

    /// Confidence in the signal (0.0 = no data, 1.0 = fully warmed up)
    pub fn confidence(&self) -> f64 { ... }
}

Add Signal Workflow

Step-by-step process for adding a new predictive signal. Follow measurement-before-modeling: define what you're predicting, log it, measure baseline, then build.

Step 1: Define the Signal

Before writing code, answer:

What does it predict? (price direction, fill probability, adverse selection, volatility)
At what horizon? (100ms, 1s, 10s, 60s)
What is the prediction target metric? (Brier Score for binary, IR for continuous)
What is the baseline? (naive predictor, e.g., always predict 50% for binary)

Step 2: Implement the Estimator

Create a new file in src/market_maker/estimator/:

// src/market_maker/estimator/my_signal.rs

pub struct MySignalEstimator {
    // State for online estimation
    // Use EWMA, rolling windows, or Bayesian updates
}

impl MySignalEstimator {
    pub fn new(config: MySignalConfig) -> Self { ... }

    /// Update with new market data. Called on every relevant event.
    pub fn update(&mut self, data: &MarketData) { ... }

    /// Get current signal value, normalized to a useful range.
    /// Document units in the return type or name.
    pub fn signal_value(&self) -> f64 { ... }

    /// Confidence in the signal (0.0 = no data, 1.0 = fully warmed up)
    pub fn confidence(&self) -> f64 { ... }
}

Add Signal

Add Signal Workflow

Step 1: Define the Signal

Step 2: Implement the Estimator

Add Signal

Add Signal Workflow

Step 1: Define the Signal

Step 2: Implement the Estimator

Conventions

Step 3: Register in mod.rs

Step 4: Wire into Signal Integration

Step 5: Add Model Gating

Step 6: Add Prediction Logging

Step 7: Set Up Calibration

Step 8: Verify

Step 9: Validate Live

Checklist

Llm Trading Agent Security

Energy Procurement

Council

Carrier Relationship Management

Market Research

Market Research