Menu

2016 APBR NBA Draft Statistical Modeling Showcase

2016 APBR NBA Draft Statistical Modeling Showcase
Jun 22, 2016, 09:25 am
With the rise in basketball analytics, NBA teams and hardcore enthusiasts have been utilizing the growing range of data sets for a wide array of purposes. While the NBA has made a concerted effort to introduce new metrics to the public, even going so far as to make SportVu and Synergy data readily available on their stat hub, data on draft eligible players isn't quite as comprehensive or readily available. Though NCAA statistics aren't always particularly easy to use given the small sample sizes, the variety in the quality of competition prospects face, the roles they play, and even the system they play in, a growing number of analysts in recent years have taken the time to carefully groom systems to project prospects based on their numbers in the college game.

APBR, the Association for Professional Basketball Research, is a forum where many of these talented individuals can discuss basketball statistical analysis, modeling, and best practices for acquiring and utilizing data. The forum is home to a passionate community which counts fans, consultants, service providers, and NBA personnel among its current and former active members.

Like last season, we put out an open call to APBR members to showcase their analytical draft projections. When making projections of any kind, aggregating information from a variety of sources tends to provide the best projection on average. Two esteemed APBR members, Nick Restifo and Jesse Fischer, have been nice enough to describe the method behind their personal NBA projections for this year's crop of prospects, show their top 14 picks, and then finally compare their 68 players with DraftExpress' mock draft. One thing to note is that these models aim to rank the best players, while our mock draft is an attempt to project where players might be drafted.

Note: Due to the varying levels of competition found in international basketball, only collegiate players were considered.

Preview on the Different NBA Draft Models, and Their Top Prospects. Full Ranking At Bottom

My name is Nick Restifo. In addition to working as an associate data scientist for a major company, I contribute to Nylon Calculus and Fansided, and consult for college basketball teams.

The first component of my draft projection system is an ensemble of a random forest model, and a gradient boosted logistic regression model, a logistic regression model, a neural network model, and a classification and regression decision tree, all predicting whether or not a player will play in the NBA. These models value factors like high school rank, points, strength of schedule, wingspan, and combine results more heavily than the other aspects of my system. My play probability models are trained on every player with a record on DraftExpress since 2002. These include almost all players in Division 1 basketball since then, as well as many players who played in international leagues across the world.

The next component of my draft model is an ensemble of a random forest model, and a gradient boosted regression model, a generalized linear regression model, a neural network model, and a classification and regression decision tree, all predicting success in the NBA assuming a player makes it that far. This production ensemble assigns similar influence to some factors when compared to the NBA play ensemble, but items such as age, steal rate, and assists carry the most weight here. Fewer variables are considered important enough to merit inclusion in the NBA production models. The combine test statistics, for example, do not make the cut. My NBA production models are trained on all NBA players who played more than a total of 50 minutes in at least one NBA season for which pre-draft information is available on DraftExpress since 2002.

While the target for the play probability models is simply whether or not a player played in the NBA, the target variable I train on and predict for the NBA production models is a player's two-year peak (in some cases one-year) of a scaled blend of NPI RAPM, WS, and BPM. Predicting WS alone actually results in the most accurate predictions from pre-draft production data, but since the ability to predict a number and the value of that prediction are two separate things, I opt to use the blend, combining the predictability of WS with the often more telling value of RAPM and BPM.

Both ensemble models are built on a weighted average, with each base model weighted in the ensemble by its ability to predict out of sample. To reach my overall rating, I simply take the success of a player should he play in the NBA to the power of his predicted probability of NBA play, making the process somewhat of an exercise in conditional probability. Taking the power as opposed to the product of these two values produced better out of sample results. While this approach may have flaws, it has undeniable flexibility. It can be applied without reliance on subjective filters for training or evaluation to any player playing in the major competitive basketball environments and provide a decent estimate of his value as a future NBA player.

ProspectRanking
Ben Simmons1
Brandon Ingram2
Henry Ellenson3
Dejounte Murray4
Isaiah Whitehead5
Jakob Poeltl6
Kay Felder7
Jamal Murray8
Kris Dunn9
Tyler Ulis10
Jaylen Brown11
Kyle Wiltjer12
Dorian Finney-Smith13
Brice Johnson14


My name is Jesse Fischer and I work at Amazon as a Senior Software Engineer. My academic background includes a degree in Computer Engineering with a minor in Mathematics from the University of Washington. I blog at [url=http://www.tothemean.comwww.tothemean.com as much as I can find time. If you haven't already, please check out our annual analytics draft board compilation (http://tothemean.com/tools/draft-models/, 2016 updates coming soon!). I can be found on twitter at @jessefischer33 (https://twitter.com/jessefischer33.

My "Longevity" draft model optimizes for "long term value" as defined by a player's max five-year "Value over Replacement Player" (VORP). VORP is based on the stat Box Plus/Minus (BPM) (link) and accounts for playing time, allowing injuries/durability/coaching preferences to be factored in, which is important when measuring for playing longevity. For active players, max VORP values are predicted based on age, VORP trajectory, playing time trajectory, etc.

The "Longevity" model incorporates individual and team performance (traditional and advanced stats), measurables (age, height, weight, etc), athletic abilities (NBA combine data), situation (teammate quality, competition, pace, position, playing time, era), and scouting (actual/expected draft rank). Additionally, the newest iteration of my model now includes metrics built from individual game logs. Individual game logs better capture information about how well a player performs against different levels of competition and/or playing style, which can be lost in the noise when simply looking at season averages (even if scaling by the strength of schedule and/or pace).

The model is trained on a data set of every college player over the last 25 years, reduced down to players with any NBA potential (as determined by NBA probability estimates, which are based on basic performance statistics). Players who never made the NBA are assumed to have replacement player value. Since playing styles have shifted greatly over the last 25 years, the performance of a player in a certain area is also measured about his peers from that season which helps make effectiveness in certain areas (i.e. 3's) more comparable across time. Lastly, the final model is a blend of many different individual models. The individual models consist of various machine learning algorithms (both linear and non-linear), all tuned in different ways.

ProspectRanking
Ben Simmons1
Kris Dunn2
Brandon Ingram3
Jakob Poeltl4
Jamal Murray5
Buddy Hield6
Deyonta Davis7
Domantas Sabonis8
Brice Johnson9
Denzel Valentine10
Taurean Prince11
Tyler Ulis12
Jaylen Brown13
Marquese Chriss14


We'd like to thank Jesse and Nick for their efforts and willingness to share and offer an invitation for others to join them when we renew this series of articles for the 2017 NBA Draft next spring. Here are the composite rankings color coded to help make everything a bit more clear (red is better, yellow is worse).

Player Nick Jesse DX Top 100 DX Mock Overall Average Nick & Jesse Average DX Average
Ben Simmons 1 1 2 1 1.25 1.00 1.50
Brandon Ingram 2 3 1 2 2.00 2.50 1.50
Kris Dunn 9 2 3 4 4.50 5.50 3.50
Jakob Poeltl 6 4 7 8 6.25 5.00 7.50
Jamal Murray 8 5 5 7 6.25 6.50 6.00
Jaylen Brown 11 13 4 6 8.50 12.00 5.00
Henry Ellenson 3 17 12 9 10.25 10.00 10.50
Deyonta Davis 16 7 9 12 11.00 11.50 10.50
Tyler Ulis 10 12 17 19 14.50 11.00 18.00
Marquese Chriss 32 14 10 3 14.75 23.00 6.50
Buddy Hield 44 6 6 5 15.25 25.00 5.50
Demetrius Jackson 21 15 14 13 15.75 18.00 13.50
Skal Labissiere 30 16 8 10 16.00 23.00 9.00
Brice Johnson 14 9 22 20 16.25 11.50 21.00
Denzel Valentine 28 10 11 18 16.75 19.00 14.50
Taurean Prince 34 11 16 15 19.00 22.50 15.50
Dejounte Murray 4 25 24 25 19.50 14.50 24.50
Domantas Sabonis 43 8 15 14 20.00 25.50 14.50
Malik Beasley 18 22 19 23 20.50 20.00 21.00
Diamond Stone 17 23 25 22 21.75 20.00 23.50
Cheick Diallo 36 19 20 16 22.75 27.50 18.00
Malachi Richardson 19 35 27 24 26.25 27.00 25.50
Damian Jones 48 24 18 17 26.75 36.00 17.50
Chinanu Onuaku 38 18 28 27 27.75 28.00 27.50
DeAndre Bembry 60 21 21 21 30.75 40.50 21.00
Kay Felder 7 34 41 41 30.75 20.50 41.00
Gary Payton II 20 37 35 35 31.75 28.50 35.00
Isaiah Whitehead 5 38 42 42 31.75 21.50 42.00
Malcolm Brogdon 51 20 29 29 32.25 35.50 29.00
Pascal Siakam 25 28 38 38 32.25 26.50 38.00
A.J. Hammons 45 30 30 30 33.75 37.50 30.00
Robert Carter 47 27 31 31 34.00 37.00 31.00
Ben Bentil 41 31 32 32 34.00 36.00 32.00
Michael Gbinije 26 32 39 39 34.00 29.00 39.00
Caris LeVert 42 29 33 33 34.25 35.50 33.00
Patrick McCaw 68 26 23 28 36.25 47.00 25.50
Anthony Barber 15 54 40 NR 36.33 34.50 40.00
Stephen Zimmerman Jr. 27 56 26 NR 36.33 41.50 26.00
Kyle Wiltjer 12 43 56 NR 37.00 27.50 56.00
Dorian Finney-Smith 13 49 43 43 37.00 31.00 43.00
Wade Baldwin IV 55 48 13 NR 38.67 51.50 13.00
Jake Layman 52 36 36 36 40.00 44.00 36.00
Georges Niang 29 40 51 NR 40.00 34.50 51.00
Wayne Selden Jr. 22 66 34 NR 40.67 44.00 34.00
Isaiah Briscoe 40 42 NR NR 41.00 41.00 NR
Perry Ellis 23 51 50 NR 41.33 37.00 50.00
Marcus Paige 24 55 48 NR 42.33 39.50 48.00
Prince Ibeh 63 33 37 37 42.50 48.00 37.00
Jameel Warney 37 50 NR NR 43.50 43.50 NR
Sheldon McClellan 33 52 45 45 43.75 42.50 45.00
Jarrod Uthoff 50 41 44 NR 45.00 45.50 44.00
Yogi Ferrell 31 58 47 NR 45.33 44.50 47.00
Isaiah Taylor 46 46 49 NR 47.00 46.00 49.00
Josh Hart 54 44 NR NR 49.00 49.00 NR
Derrick Jones Jr. 53 47 52 NR 50.67 50.00 52.00
Joel Bolomboy 56 53 NR 44 51.00 54.50 44.00
Josh Adams 64 39 NR NR 51.50 51.50 NR
Shawn Long 35 61 59 NR 51.67 48.00 59.00
Danuel House 39 68 NR NR 53.50 53.50 NR
Troy Williams 49 59 54 NR 54.00 54.00 54.00
Damion Lee 59 65 46 NR 56.67 62.00 46.00
Fred VanVleet 67 45 60 NR 57.33 56.00 60.00
Ron Baker 57 57 58 NR 57.33 57.00 58.00
James Webb 62 60 53 NR 58.33 61.00 53.00
Zach Auguste 58 63 57 NR 59.33 60.50 57.00
Julian Jacobs 61 62 62 NR 61.67 61.50 62.00
Alex Caruso 65 64 61 NR 63.33 64.50 61.00
Wes Washpun 66 67 NR NR 66.50 66.50 NR


Notes: The Mock Draft list only has 45 prospects eligible for this exercise. The overall top 100 prospect list only had 62.

Recent articles

  • Ben Simmons nba mock draft
    Ben Simmons nba mock draft
    Age: 21.1
    Height: 6'10"
    Wingspan: 7'0 ¼"
    Weight: 239
    19.2 Points
    11.9 Rebounds
    4.8 Assists
    29.9 PER
  • Brandon Ingram nba mock draft
    Brandon Ingram nba mock draft
    Age: 20.0
    Height: 6'9"
    Wingspan: 7'3"
    Weight: 196
    26.0 Points
    1.0 Rebounds
    3.0 Assists
    25.6 PER
  • Henry Ellenson nba mock draft
    Henry Ellenson nba mock draft
    Age: 20.6
    Height: 7'0"
    Wingspan: 7'2 ¼"
    Weight: 242
    5.4 Points
    2.6 Rebounds
    0.2 Assists
    12.7 PER
  • Dejounte Murray nba mock draft
    Dejounte Murray nba mock draft
    Age: 20.9
    Height: 6'5"
    Wingspan: 6'9 ½"
    Weight: 170
    6.5 Points
    6.0 Rebounds
    3.0 Assists
    1.3 PER
  • Isaiah Whitehead nba mock draft
    Isaiah Whitehead nba mock draft
    Age: 22.4
    Height: 6'5"
    Wingspan: 6'8 ¾"
    Weight: 210
    13.2 Points
    4.6 Rebounds
    3.0 Assists
    19.0 PER
  • Jakob Poeltl nba mock draft
    Jakob Poeltl nba mock draft
    Age: 21.8
    Height: 7'1"
    Wingspan: 7'2 ¾"
    Weight: 239
    5.6 Points
    4.0 Rebounds
    0.6 Assists
    21.1 PER
  • Kay Felder nba mock draft
    Kay Felder nba mock draft
    Cavaliers
    Kay Felder PG
    Age: 22.4
    Height: 5'10"
    Wingspan: 6'2 ½"
    Weight: 177
    8.8 Points
    2.2 Rebounds
    3.7 Assists
    10.5 PER
  • Jamal Murray nba mock draft
    Jamal Murray nba mock draft
    Age: 20.5
    Height: 6'5"
    Wingspan: 6'6 ½"
    Weight: 201
    9.9 Points
    2.6 Rebounds
    2.1 Assists
    12.0 PER
  • Kris Dunn nba mock draft
    Kris Dunn nba mock draft
    Timberwolves
    Kris Dunn PG
    Age: 23.4
    Height: 6'4"
    Wingspan: 6'9 ½"
    Weight: 205
    11.0 Points
    4.0 Rebounds
    3.0 Assists
    6.5 PER
  • Tyler Ulis nba mock draft
    Tyler Ulis nba mock draft
    Age: 21.6
    Height: 5'10"
    Wingspan: 6'2"
    Weight: 149
    7.3 Points
    1.6 Rebounds
    3.7 Assists
    12.9 PER
  • Jaylen Brown nba mock draft
    Jaylen Brown nba mock draft
    Age: 20.8
    Height: 6'7"
    Wingspan: 6'11 ¾"
    Weight: 223
    10.3 Points
    5.3 Rebounds
    1.7 Assists
    10.2 PER
  • Kyle Wiltjer nba mock draft
    Kyle Wiltjer nba mock draft
    Age: 24.8
    Height: 6'10"
    Wingspan: 7'0 ¼"
    Weight: 243
    5.8 Points
    2.3 Rebounds
    0.3 Assists
    17.2 PER
  • Dorian Finney-Smith nba mock draft
    Dorian Finney-Smith nba mock draft
    Age: 24.3
    Height: 6'8"
    Wingspan: 6'11 ¾"
    Weight: 215
    8.0 Points
    6.2 Rebounds
    2.3 Assists
    12.4 PER
  • Brice Johnson nba mock draft
    Brice Johnson nba mock draft
    Age: 23.1
    Height: 6'11"
    Wingspan: 7'0 ½"
    Weight: 209
    14.4 Points
    5.2 Rebounds
    0.8 Assists
    22.5 PER
  • Buddy Hield nba mock draft
    Buddy Hield nba mock draft
    Age: 23.7
    Height: 6'5"
    Wingspan: 6'9 ¼"
    Weight: 212
    16.7 Points
    3.7 Rebounds
    1.0 Assists
    17.7 PER
  • Deyonta Davis nba mock draft
    Deyonta Davis nba mock draft
    Age: 20.7
    Height: 6'11"
    Wingspan: 7'2 ½"
    Weight: 237
    7.3 Points
    7.5 Rebounds
    0.5 Assists
    17.3 PER
  • Domantas Sabonis nba mock draft
    Domantas Sabonis nba mock draft
    Age: 21.3
    Height: 6'10"
    Wingspan: 6'10 ½"
    Weight: 231
    5.8 Points
    3.5 Rebounds
    1.0 Assists
    6.9 PER
  • Denzel Valentine nba mock draft
    Denzel Valentine nba mock draft
    Age: 23.8
    Height: 6'6"
    Wingspan: 6'10 ¾"
    Weight: 210
    13.0 Points
    6.2 Rebounds
    3.6 Assists
    11.3 PER
  • Taurean Prince nba mock draft
    Taurean Prince nba mock draft
    Age: 23.0
    Height: 6'8"
    Wingspan: 6'11 ½"
    Weight: 220
    13.3 Points
    2.5 Rebounds
    1.5 Assists
    8.1 PER
  • Marquese Chriss nba mock draft
    Marquese Chriss nba mock draft
    Age: 20.1
    Height: 6'10"
    Wingspan: 7'0 ¼"
    Weight: 233
    12.2 Points
    5.5 Rebounds
    0.7 Assists
    15.7 PER

Twitter @DraftExpress

DraftExpress Shop