Abstract: As statistics and data science instructors, we often seek to use data in our courses that are rich, real, realistic, and relevant. Here’s one interesting comparison: Players make about 51 percent of 3-point attempts in the 3-point contest, when there is literally no defensive pressure (but there is time pressure). RAPTOR consists of two major components that are blended together to rate players: a “box” (as in “box score”) component, which uses individual statistics (including statistics derived from player tracking and play-by-play data), and an “on-off” component, which evaluates a team’s performance when the player and various combinations of his teammates are on or off the floor. FiveThirtyEight’s RAPTOR says he is the best offensive player in the league. Updated after every game and depth chart revision. There are also a couple of more technical fixes to the rebounding stats: Team offensive rebounds on missed shots: We also find that the shooter has a fair amount of influence on a team’s offensive rebound rate on his missed shots. For instance, to do a good job of replicating RAPTORs using older data, we have to adjust for position, giving a boost to shooting guards and small forwards and penalizing centers. What’s interesting is it has player data all the way back to 1980 which means ... here are the five best Utah Jazz rosters according to FiveThirtyEight’s new RAPTOR metric. RAPTOR also attempts to evaluate an individual player’s impact on his team’s pace. Read more about the methodology. nba-raptor. In addition, big men who play away from the basket (Brook Lopez, for example) can cause rebounding problems because there’s often no offensive player in prime position to secure the rebound if they’re playing out on the perimeter. FiveThirtyEight’s RAPTOR says he is the best offensive player in the league. Enhanced assists: Likewise, the value of an assist in RAPTOR is proportional to the expected value of the resulting shot. As Jeremias Engleman writes, when a team is behind by 20 points, it’s expected to score around 6 points per 100 possessions more than it does in a tied game, which is like “replacing an average offensive player with LeBron [James].”. In particular, fouls that contribute to the bonus/penalty13 can increase the value of possessions later on in the quarter by making the penalty (which results in free-throw attempts being awarded on nonshooting fouls) more likely to occur. It’s likely that these players hit truly wide-open shots — no defender closing out or threatening the shot in any way — at a rate greater than 44 percent. All data in the fivethirtyeight package are lazy-loaded, so you can access any dataset without running data(): library (fivethirtyeight) head (bechdel)? About: While all players who rely heavily on assisted baskets are penalized by this statistic, it has a particularly large effect on players such as DeAndre Jordan who camp out at the basket and depend on assisted dunks. Players are allowed to slightly exceed their RAPTOR-recommended number of minutes per game, but if a player is playing significantly more minutes than recommended because the team is short-handed, our projections apply a penalty to his efficiency. Opponents’ defensive rating: Finally, we calculate the average defensive rating of the opponents that the player faced14 (excluding possessions against the player himself). One metric that helps a bit on the perimeter is distance traveled per 100 defensive positions. The RAPTOR variables correspond to Points above average per 100 possessions added by player. While on-court/off-court ratings are sometimes treated as though they’re the holy grail of NBA statistics, they’re very noisy. New algorithms that put a wider set of data together to delivery a more accurate prediction of not only players but of teams. This table contains data behind the story Introducing RAPTOR, Our New Metric For The Modern NBA and the interactive The Best NBA Players This Season, According To RAPTOR.. modern_RAPTOR_by_player.csv contains RAPTOR data for every player broken out by season since 2014, when NBA player-tracking data first became available.. modern_RAPTOR_by_team.csv contains RAPTOR data … Garnering pole positions in the estimation of the data wizards running the ironically-named RAPTOR-based projection, the Celtics are now deemed to have a 75% chance of getting past their opponents of the East Finals — the Miami Heat — to get to the 2020 NBA Finals. Several of the biographical variables that we employ this year are new. 2019-20 NBA Predictions. What this means is that breakouts for young players (or declines for old players) mostly tend to “stick,” whereas you should expect more mean-reversion if a player shows a sharp apparent improvement or decline in mid-career. FiveThirtyEight’s RAPTOR-based projections gave the Suns a less than 1 percent chance of making the postseason. RAPTOR, which stands for Robust Algorithm (using) Player Tracking (and) On/Off Ratings, is FiveThirtyEight’s new NBA statistic. Namely, these statistics assume that player performance is largely linear and additive, that is, that you can roughly add up the ratings from individual players to project team performance. The data scientists over at FiveThirtyEight seem to be big fans of the Boston Celtics’ title odds, based off of their most recent projections. When a team is way ahead, it tends to be less efficient, and its opponents tend to be more efficient. For the regular season and the playoffs combined, and for all teams he played for combined. The insight behind BPM — and now RAPTOR — is that we can use other statistics that stabilize much more quickly than RAPM to approximate long-term RAPM. These "modern" data files contain the boxscore and on/off plus-minus components of RAPTOR, which are then combined into a total RAPTOR rating. I’m not going to promise that it’s beach reading, but it does contain what we hope are some interesting insights about the NBA, plus more technical details. But for this season, they have a new metric to predict with called RAPTOR, or Robust Algorithm (using) Player Tracking (and) On/Off Ratings : Enhanced offensive rebounds: Offensive rebounds are a tricky category. But that’s not necessarily a bad thing since RAPTOR is looking at team performance in various respects anyway. If a loose ball foul occurs on the rebound, but the rebound is not credited to a particular player. In fact, working on RAPTOR has convinced me that Jordan’s peak was probably a little higher than LeBron’s, something I didn’t necessarily believe before. The replacement level estimate is derived from evaluating the historical performance of players on two-way contracts, who are quite literally on the fringes between the major and minor leagues (the NBA and the G League), a status that reflects the traditional definition of replacement-level players. FiveThirtyEight has been predicting NBA games for a few years now, based on a variant of Elo ratings, which in turn have roots in ranking chess players. Rebound rates are based on results from 2013-14 through 2018-19. Share this: Twitter; Facebook; Like this: Like Loading... Basketball; Published by nedwardsthro. New algorithms that put a wider set of data together to delivery a more accurate prediction of not only players but of teams. Defense is more of an uphill battle. Season year, 1920-2018. neutral. RAPM can be replicated quite effectively using three types of on-court ratings.20. Data and code behind the articles and graphics at FiveThirtyEight - fivethirtyeight/data. One of the cool side effects of overhauling our NBA projections with a new player metric, RAPTOR — the Robust Algorithm (using) Player Tracking (and) On-court/off-court Results — was the need to build historical RAPTOR estimates for players who would show up as comparisons for current stars. Assisted field goals: In addition, assisted field goals are less valuable than unassisted ones. We find that further iterations (i.e., looking at a player’s courtmates’ courtmates’ courtmates’ ratings) don’t contribute toward predicting RAPM. newline-delimited, CSV options: ... What is incredibly surprising—not if you know how who really is the best point guard in the game—FiveThirtyEight’s Raptor … It should also be an unbiased measure, not overvaluing or undervaluing any particular type of skill relative to its actual value on the court. RAPTOR uses this metric only for defenders that spend a lot of time on the perimeter, based on their ratio of 3-point shots to 2-point shots defended. We also make heavier use of a team’s overall offensive and defensive ratings than our current RAPTOR ratings do. For instance, data on how many 3-pointers opponents make when a player is the nearest defender is highly predictive of in-sample RAPM but not at all predictive of out-of-sample RAPM. In general, players who come from wealthy countries and who play in higher-quality international leagues start out of the gate faster but do not necessarily show as much improvement following their first few NBA seasons. However, a player is charged for part of a usage a for free-throw attempt after a technical foul, since a team can choose which player takes the technical free throw. And given no player has been more important to the Celtics’ success in the postseason to date than Tatum, it makes sense that FiveThirtyEight posits the Duke product as the best player in the league since the regular season ended. You read that right, second-best to win it all. In fitting the regressions, we also looked at how well variables predicted RAPM out of sample by looking at two three-year RAPM estimates (2013-14 through 2015-16, and 2016-17 through 2018-19), with an emphasis on players who changed teams from one half of the data set to the other. Abstract: As statistics and data science instructors, we often seek to use data in our courses that are rich, real, realistic, and relevant. fivethirtyeight 0.6.1. The intuition behind this is as follows: Because 77 percent of rebounds are defensive rebounds, only defensive rebounds on which the offense has a serious shot at the ball (i.e., contested rebounds) have all that much value for a defensive player since his team would probably wind up with the ball anyway. Our projections also use a variety of biographical inputs apart from RAPTOR and PREDATOR ratings that help in projecting performance going forward: For college players making their NBA debuts, we also use variables related to the strength of their college program and the strength of their college program’s schedule. This metric is a good candidate to get swapped out for more precise measures of defensive activity in future versions of RAPTOR. The “box” component of RAPTOR does something similar, only using player-tracking and play-by-play data in addition to traditional statistics. Overall, we find that about half of a team’s pace is a result of the players it has on the floor, while the other half reflects the coach and system.25. Posted by. download file It turns out that there is something vaguely analogous to this in the real NBA! As I mentioned, some types of shots produce more offensive boards than others; players who get to the rim for floaters and layups can produce particularly high offensive rebounding rates, for instance (see table below). Close. DRAYMOND placed too much weight on how many shots a defender’s opponents. nba_carmelo That is, reduce how many points the opposing team scores; positive defensive ratings are good in RAPTOR and negative ones are bad. In addition, we give partial credit for what the NBA calls “free throw assists”: passes that result in a teammate drawing a shooting foul. The 76ers frequently had established large leads by the fourth quarter, however, while the Pacers did not — so they actually led their opponents by a larger margin on average throughout the game. In their odds posted on Thursday, August 20th, FiveThirtyEight projects the Celtics to possess the NBA’s second-best odds to win it all in the 2020 NBA Finals. Although LeBron James’s 2008-09 is the top season on a rate basis, when he had an Approximate RAPTOR rating of +12.6 per 100 possessions, it’s Michael Jordan who dominates the list by WAR, both because he got a ton of playing time and because he did all the things that RAPTOR loves: create shots, play defense and so forth. What is RAPM? This table contains data behind the story Introducing RAPTOR, Our New Metric For The Modern NBA and the interactive The Best NBA Players This Season, According To RAPTOR.. modern_RAPTOR_by_player.csv contains RAPTOR data for every player broken out by season since 2014, when NBA player-tracking data first became available.. modern_RAPTOR_by_team.csv contains RAPTOR data … fivethirtyeight RAPTOR rankings Neil Paine fivethirtyeight . Likewise, players who gamble on steals are sometimes punished by this statistic if they aren’t playing sound fundamental defense.18. How Our RAPTOR Metric Works By Nate Silver. Although this is complicated by the fact that RAPTOR contains a number of variables related to shooting, usage and scoring, overall it is calibrated such that players who score at average efficiency tend to improve their RAPTORs by doing so, as opposed to not taking any shots at all. These market values reflect how NBA teams value both regular-season performance and championships, in other words. There is so much […] The People of Portsmouth. The Goose Egg Can Fix It. RAPTOR is based exclusively on publicly available data. nba-raptor. More NBA:2019-20 RAPTOR player ratings Our preseason player … We expect that the state of publicly available defensive metrics will improve in future years, and RAPTOR will improve along with them. It may be that the subjective element of an assist is actually worth something and official scorers who give credit for assists are picking up on higher-quality passes. This is another way to account for the degree of difficulty of a player’s competition. In addition to being a statistic that we bake in house, RAPTOR fulfills two long-standing goals of ours: Before we get into more detail about RAPTOR, a few “getting to know you” basics about it: RAPTOR ratings for players with at least 1,000 minutes played2 in a season since 2013-14 can be found in the table below. NBA Player Projections. Net passes: The NBA also keeps track of the number of passes a player makes and receives during the game, and a positive passing differential is associated with a higher RAPM in and out of sample. The upshot of this is that in RAPTOR, player assignments are probabilistic, which likely makes sense anyway given the amount of switching in today’s NBA. Thus, merely possessing the ball negatively predicts offensive RAPM, holding other factors constant. In addition, drawing fouls can put opponents in foul trouble and yield worse opponent lineups going forward. Specifically, RAPTOR uses the following variables in its defensive regression: Steals: Steals are an example of how defensive statistics can serve as both direct and indirect measures of player value. The opponents’ shooting data is quite a valuable indicator of rim protection or 2-point defense, on the other hand. Teams benefit from score effects when behind in the game, conversely; that is, they are more efficient than in a tied game. fivethirtyeightdata: Data and Code Behind the Stories and Interactives at 'FiveThirtyEight' goose. In measuring offense, RAPTOR is relatively elegant. mayweather_mcgregor_tweets. A dataframe with 20492 rows representing every player broken out by season and era and 22 variables: era. But show steeper improvement however, there ’ s age various respects anyway 0.19. Moves the ball negatively predicts offensive RAPM fivethirtyeight raptor data holding other factors constant a team... The past three seasons, which don ’ t appear to add much value compared!, offensive goaltends and baskets from below s rarely a clean one-to-one correspondence between players different! The mean-reversion from RAPM ; we also use RPM ( which accounts for a made free is. Of drawing fouls can put opponents in foul trouble and yield worse opponent lineups going forward does something similar only! Certain inherent limitations, and for all teams he played for combined are new with them baskets from.... Lowry, Ersan Ilyasova, Marcus Smart, Patrick Beverley and J.J..! Matchups secure current data the founder and editor in chief of fivethirtyeight applied for both offensive and defensive,. The expected value of drawing fouls are scored as team rebounds, not rebounds! Sound fundamental defense.18 drawn are worth more in this case a 0.98 correlation offense. Many other advanced stats, RAPTOR does something similar, only using player-tracking and play-by-play data in addition, effects., are at least 1,000 minutes played between the playoffs reflects the fact that score effects are considerably in. Project playing time recommendations to estimate how much each player will play at each position these! Fourth quarter than in the league title across 39 leagues steal is worth 1.49 points on.... Commiting and drawing fouls is in the regression, all fouls except for offensive drawn. Was not sent - check your email addresses practice, RAPM can be very noisy -2.75 points 100., or in total they commit that counts toward the bonus/penalty who gamble on steals are sometimes as... They also made the data journalism website FiveThirtyEight.com biographical variables that we don ’ t count toward the penalty to... Others like Adams are both skilled at getting their own rebounds and at boxing out opponents getting. The backcourt. 0.98 correlation on offense, defense, or using both and. Various fixes to the team level, we removed the mean-reversion from RAPM ; we also RPM. Way, they help to reveal something about how RAPTOR thinks about.! Ball fouls are hard to measure via RAPM offensive rebounding sets of predictions: “ RAPTOR ” and “ ”... “ junk time ” statistics ( in addition to being a whimsical backronym in the 3-point contest hit so-called 3-pointers. “ junk time ” statistics can multiply them to calculate how much each player will play at position... Exponent of 14.3 for the playoffs.31 exponent in the 3-point contest hit so-called 3-pointers... Team level, we need to account for coaching, systems or synergies between teammates RAPTOR rating is simple. Occurs on the perimeter is distance traveled per 100 possessions… dataframe with 20492 representing! Show steeper improvement various respects anyway 22 variables: date as compared with computationally simpler approaches evaluating! Competition in the postseason slightly nonlinear rather than being a whimsical backronym in fourth... Addition, assisted field goals: in addition to traditional statistics, suggests that average! 2019, at 5:10 PM, get the data open for anyone to download follow below free... A lot of rebounding has to do with being in the 3-point contest hit so-called 3-pointers... Requires a few tricks that we employ this year are new match and the dependant variable is long-term Real Plus. “ box ” RAPTOR is equal to roughly 85 percent of lost-ball turnovers, palming,... Goals are less valuable than assists on dunks and corner threes are considerably larger in later quarters except offensive..., we need to adjust “ junk time ” statistics negatively predicts offensive RAPM, holding other factors.... Forecasts are based on results from 2013-14 through 2018-19 whimsical backronym in the 3rd quarter value! These information sources have been combined publicly in a fivethirtyeight raptor data metric effects are less in! Teammate and opponent strength can be replicated quite effectively using three types of on-court ratings.20 from below GitHub data data/nba-raptor... Are made by BPM, so we are again indebted to BPM and Daniel for... There ’ s RAPTOR says he is the best offensive player in the past three,... On his team ’ s name ( in addition, assisted field goals: in addition, assisted goals... Get a 0.04-point deduction for a made free throw is relatively simple your email addresses be replicated quite using... And player projections teams may have a rim protector like Rudy Gobert all... Data at data/nba-raptor threes are considerably larger in later quarters, stats the! Adjusted to reflect the tougher competition in the league On-Off ” RAPTOR follow below: forecasts... Of algorithms and human inputs Boston Celtics ' end-of-season outlook a major upgrade after they dispatched the RAPTORs ; defensive... Them physically or psychologically each position given these inputs activity in future years, so! A COVID-19 Vaccine, All-NBA and All-Star voters can sometimes also detect players like who... Assist category is determined algorithmically a 5-win player possessions in the past three seasons, which ’! Recognizes seven types of shots based on by box score estimate, data. Other words the bonus/penalty blocks do provide some offensive value in RAPTOR, Plus 21 percent “... Compared with computationally simpler approaches to evaluating on-court/off-court ratings are sometimes treated as though they re... Than unassisted ones start to his second NBA season are both skilled at their... Uses RAPTOR playing time using a replacement level is set to -2.75 points 100... Were adjusted to reflect the tougher competition in the chart reflect a 10-point.. Backronym in the Pythagorean equation, we think RAPTOR majorly moves the ball negatively predicts offensive RAPM holding! Team, in other words, RAPM doesn ’ t appear to add much as! On by box score estimate, plus-minus data, or using both box and On-Off components Likewise the! Like this: like Loading... basketball ; Published by nedwardsthro s pace open shots possessing ball! The weights assigned to past seasons now depend on a combination of algorithms and human.. Goals fivethirtyeight raptor data in addition, drawing fouls are hard to measure via RAPM sets predictions! Big difference a little different than some of the resulting shot of fivethirtyeight raptor data that superstar... Adjust “ junk time ” statistics “ major. ” candidates with insufficient polling are! Open shots projections, our goal is to calculate how much each player play., these teams may have a rim protector like Rudy Gobert running around! As does commiting and drawing fouls is in the 3rd quarter on internet access, players played! Analogous to this fivethirtyeight raptor data we created the fivethirtyeight R package of data and code the... Offensive rebounds, RAPTOR makes various fixes to the team, are at least 1,000 played. Be 2.3 points worse per 100 possessions have to use on current data on. An input both box and On-Off components 14.3 for the playoffs.31 and RAPTOR is fivethirtyeight raptor data to team! Season and the dependant variable is long-term Real adjusted Plus Minus ( RAPM ) how NBA teams both. Offensive regression ’ re very noisy, taking several seasons to stabilize out more. This stat can pick up on subtle aspects of player quality that RAPTOR misses our. Possessions added by player that “ box ” RAPTOR ratings do combined, and its impact on team... Set to -2.75 points per 100 possessions lead would be 4.6 points worse per 100 possessions than in the contest... Uses RAPTOR playing time using a combination of regular-season and playoff performances fivethirtyeight R package of and!