Leading up to the 2018 NBA Draft on June 21st, we will be using our NBA Draft Models (PNSP Model, Role Probability Model, and Similarity Scores) to investigate this year’s top prospects. These Prospect Profiles look at which stats affect NBA projections, present unique data points from a player’s stats, and give relevant comparisons to current NBA players. You can find all of our Prospect Profiles here or through the header menu above (NBA –> NBA Draft –> Prospect Profiles). In today’s article, we look at Marvin Bagley III.
Continue reading Prospect Profile: Marvin Bagley III
Category Archives: Basketball
Prospect Profile: Wendell Carter Jr.
Leading up to the 2018 NBA Draft on June 21st, we will be using our NBA Draft Models (PNSP Model, Role Probability Model, and Similarity Scores) to investigate this year’s top prospects. These Prospect Profiles look at which stats affect NBA projections, present unique data points from a player’s stats, and give relevant comparisons to current NBA players. You can find all of our Prospect Profiles here or through the header menu above (NBA –> NBA Draft –> Prospect Profiles). In today’s article, we look at Wendell Carter Jr.
Prospect Profile: Shai Gilgeous-Alexander
Leading up to the 2018 NBA Draft on June 21st, we will be using our NBA Draft Models (PNSP Model, Role Probability Model, and Similarity Scores) to investigate this year’s top prospects. These Prospect Profiles look at which stats affect NBA projections, present unique data points from a player’s stats, and give relevant comparisons to current NBA players. You can find all of our Prospect Profiles here or through the header menu above (NBA –> NBA Draft –> Prospect Profiles). In today’s article, we look at yet another Kentucky freshman, Shai Gilgeous-Alexander.
Continue reading Prospect Profile: Shai Gilgeous-Alexander
2018 Similarity Score Tool
Select any 2018 NBA Draft prospect from the drop-down menu below to view their top 10 most similar college basketball players. Similarity Scores provide insight into how a player will translate to the NBA based on how their historical comparisons have performed in the NBA. This model considers a player’s college production, physical measurements, and age/experience to generate their most similar historical players. For more background on the calculation of the similarity scores, see this article. This model is one of three pieces that we use to evaluate the NBA potential of college players, with the other two being PNSP and NBA Role Probability Model.
Continue reading 2018 Similarity Score Tool
2018 NBA Role Probability Model
The NBA Role Probability Model predicts the likelihood that a given college basketball player becomes an All-Star, starter, bench player, or does not make it in the NBA. The model considers individual box score statistics, team-level statistics (e.g. strength of schedule), physical measurements, high school scouting rank, position, and age/experience to predict the probability of a player landing each NBA role. For more detail on how this model is formulated, see this article. The Role Probability model is one of three pieces that we use to evaluate the NBA potential of college and international players, with the other two being PNSP and Similarity Scores. In the table below, you can find the model’s predicted probabilities for each 2018 prospect landing in a given role in the NBA.
Continue reading 2018 NBA Role Probability Model
2018 NBA Finals
Through three rounds, we have gone 10/14 in series predictions. Two of these incorrect picks have come from series involving the Cavaliers. As we have seen in prior years, our models have a hard time assessing the Cleveland Cavaliers because they consistently under perform in the regular season. In the Championship round, our models are siding with the Golden State Warriors. Four of our five models picked the Warriors to win, and the average probability across the five predictions is 0.69. We will continue to update the table below following each game in the series!
2018 Peak NBA Statline Projection Model
Peak NBA Statline Projection (PNSP) is a model used to project NBA success for college and International basketball players. PNSP considers each player’s individual and team statistics, physical measurements, high school scouting ranking, and age/experience. The PNSP model returns a single rating value from 0 to 100, with higher values indicating a “better” NBA prospect. We provide a detailed article outlining how PNSP is formulated here, and PNSP rankings from previous years can be found here. Below are a few highlights from PNSP’s ratings for the 2018 NBA Draft Class.
Model 284 Podcast: NBA Draft Models
On this episode of the Model 284 Podcast, Sam and Marc are joined by fellow Model 284er Jack Werner to give some background on our NBA Draft models, discuss draft theory and positional value, and look a bit at the 2018 draft class.
Podcast (model-284-podcast): Play in new window | Download
2018 NBA Conference Finals
The probabilities for our second round predictions were generated from four unique statistical models that are built on team and player level data from the regular season. Our prediction for each series comes from computing the average of these four models. Keep in mind that teams who had significant injuries in the regular season may be undervalued by the models. Likewise, teams who have players that played through the regular season but are injured for the playoffs are likely overvalued. For more information on our modeling techniques check out our methodologies page. Continue reading 2018 NBA Conference Finals
My Model Monday: Deep Dive Into Technical Fouls
Tensions between players and NBA officials have been on the rise over the past couple years. In the 2016 – 2017 season, referees called 917 technical fouls, and in the 2017 – 2018 season that number increased to 946. Players and coaches are antagonizing referees more and more, forcing referees into handing out more technical fouls. On most occasions, a technical fouls is due to a player or coach letting their emotions get the best of them. Other times, the technical may have been drawn intentionally to send a message. When a technical foul is called, the opposing team is awarded a free throw, but the overall effect on the game doesn’t always end there. In this article, I investigate how technical fouls effect the game from the perspective of the teams involved and the officials. All of the data in this analysis came from basketball-reference.com. Continue reading My Model Monday: Deep Dive Into Technical Fouls