Our Methodology

The Predictability Score is not just a random number; it's a robust statistical measure designed to quantify the consistency and reliability of any data series. This page provides a high-level overview of the principles behind our calculation.

Core Concept: Signal vs. Noise

At its heart, every predictive system or data set contains two components:

• The Signal: The underlying trend or average performance. This is the value you are trying to capture.
• The Noise: The random, unpredictable fluctuations around the signal. This is the volatility or error.

A system is "predictable" when the signal is strong and the noise is low. Our score measures this relationship.

The Calculation: Coefficient of Variation (CV)

Our algorithm is based on a widely accepted statistical measure called the Coefficient of Variation (CV). The CV is a standardized measure of dispersion, calculated as:

CV = Standard Deviation / |Average|

This formula tells us how large the "noise" (Standard Deviation) is relative to the "signal" (the absolute value of the Average). A lower CV indicates higher predictability.

From CV to a 0-100 Score

To make the result intuitive, we convert the raw CV into a simple 0-100 score using an exponential decay function:

Score = 100 * e-CV

This model ensures that:

• A perfectly consistent data set (CV = 0) receives a score of 100.
• As volatility increases relative to the average, the score smoothly and realistically decreases towards 0.

This approach provides a more rigorous and honest assessment of predictability than a simple linear scale, making it a reliable tool for serious analysis in finance, sports analytics, and business operations.