All posts by Marc Richards

The Methodology Behind our NFL Playoff Models

This article provides some background on the components of each NFL Playoff Model. By making use of multiple models that are comprised of different modeling techniques and variables, we can better assess each game. For example, if all the models are predicting the Pittsburgh Steelers to beat the Miami Dolphins, we can feel very confident in picking the Steelers to win. If the models are split, we can explore each model individually based on their predictors to identify areas where the model may be taking into account less than perfect information. For instance, if one model emphasizes defensive performance and Seattle is currently missing Earl Thomas, maybe that model does not represent Seattle as accurately as the others. Ultimately, by looking at multiple models we are able to reduce the noise inherent in all predictive models.

Continue reading The Methodology Behind our NFL Playoff Models

2016 NFL Playoff Simulation

Using probabilities from our five NFL Playoff Models, we have run a number of simulations for the upcoming 2016 NFL Playoffs. This allows us to estimate how often each team makes the division round, conference championship, Super Bowl, and ultimately win the Super Bowl. In order to do this, we took each game and generated a random number between 0 and 1. If the random number is less than our predicted probability of the home team winning, then we advance the home team as the winner of that game (and vice versa if the random number is greater than our probability). For example, Model 1 has a probability of 0.85 that the Houston Texans will beat the Oakland Raiders. If the random number is 0.95, we would pick the Raiders to advance, and if the random number is 0.55, we would pick the Texans to advance. This methodology was applied to the entire NFL Playoff bracket, running 10,000 Playoff simulations for each of our five models (so, each model generates 10,000 brackets and 10,000 super bowl champions).
Continue reading 2016 NFL Playoff Simulation

2011 Peak NBA Statline Projection Model

Peak NBA Statline Projection (PNSP) is a model used to project NBA success for college basketball players based upon their individual and team college basketball statistics, physical measurements, high school scouting rankings, and college basketball experience. The Peak NBA Statline Projection model returns a single rating value from 0 to 100. A higher rating value indicates a “better” NBA prospect. We provide a more detailed article outlining how PNSP is formulated here. Below are a few highlights of PNSP’s ratings for the 2011 NBA Draft Class, as well as a full list of PNSP’s top 20 players of the class.

Continue reading 2011 Peak NBA Statline Projection Model

2016 Peak NBA Statline Projection Model

Peak NBA Statline Projection (PNSP) is a model used to project NBA success for college basketball players based upon their individual and team college basketball statistics, physical measurements, high school scouting rankings, and college basketball experience. The Peak NBA Statline Projection model returns a single rating value from 0 to 100. A higher rating value indicates a “better” NBA prospect. We provide a more detailed article outlining how PNSP is formulated here. Below are a few highlights of PNSP’s ratings for the 2016 NBA Draft Class, as well as a full list of PNSP’s top 20 players of the class.

Continue reading 2016 Peak NBA Statline Projection Model

Peak NBA Statline Projection Model Overview

Introduction

The following is a walk-through of our NBA Prospecting model called Peak NBA Statline Projection (PNSP). PNSP is a prospecting tool that synthesizes numerous variables for college basketball players to predict their NBA success. PNSP seeks to project peak potential success of a college basketball player in the NBA by returning a single rating value (ranging from 0 to 100) that is derived from all available information on a given player.

Continue reading Peak NBA Statline Projection Model Overview