... but … This data is based on by box score estimate, plus-minus data, or using both box and on-off components. In addition, we used our basketball knowledge to inform our choices of parameters. newline-delimited, CSV options: A dataframe with 20492 rows representing every player broken out by season and era and 22 variables: era. That is, a 10-win player is slightly more than twice as valuable as a 5-win player. These "historical" data files use full player-tracking RAPTOR for seasons since 2014, a version of RAPTOR that mixes boxscore value estimates with single-year regularized plus-minus data for seasons from 2001 to 2013, and a version of RAPTOR that only uses a boxscore estimate of value for the seasons from 1977 through 2000. Opponents’ free throws made: RAPTOR deducts value for free throws made on fouls committed by the defensive player. In addition, we give partial credit for what the NBA calls “free throw assists”: passes that result in a teammate drawing a shooting foul. Nate Silver’s FiveThirtyEight uses statistical analysis — hard numbers — to tell compelling stories about elections, politics, sports, science, economics and lifestyle. In our various regression specifications, it was ambiguous whether a better statistical fit was produced by using all 3-point attempts or instead weighting 3-point attempts based on how closely contested they were. The “box” component of RAPTOR does something similar, only using player-tracking and play-by-play data in addition to traditional statistics. @natesilver538. MLB Elo. However, because we also avoided variables that performed poorly in out-of-sample tests in constructing RAPTOR, it and PREDATOR are extremely well-correlated. Distance traveled, for perimeter defenders only: As mentioned, current publicly available defensive metrics are more effective at measuring interior/rim defense than perimeter defense. 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. raptor_by_player. Naturally, the Suns then proceeded to take the bubble by storm, going 8 … 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. Players who are adept at inducing offensive fouls include Kyle Lowry, Ersan Ilyasova, Marcus Smart, Patrick Beverley and J.J. Barea. For these reasons, RAPM is not a great measure for use in a projection system, when our data needs are more time sensitive — e.g., if we want to see how much a player such as De’Aaron Fox improves from one season to the next. More specifically, we fit a series of regression coefficients using a six-year dataset of RAPM as provided to us by Ryan Davis, with the six years matching the six seasons (2013-14 through 2018-19) for which player tracking data is available. Again adjusted for strength of opposition. How Our RAPTOR Metric Works By Nate Silver. We can then use Pythagorean expectation to estimate a team’s winning percentage. Adjusted for score effects, they were a better team, in other words. We also find that this comparatively simple way to evaluate a player’s on-court/off-court impact not only replicates RAPM extremely well in sample but also predicts out-of-sample RAPM as well or slightly better than RAPM itself, depending on the regression specification. Opponents’ field goals made and attempted: Earlier this year, we introduced DRAYMOND, a measure of on-ball defense based on the NBA’s opponents’ shooting statistics. This data is based on by box score estimate, plus-minus data, or using both box and on-off components. Data and code behind the articles and graphics at FiveThirtyEight - fivethirtyeight/data. Opponents’ offensive rating: RAPTOR calculates the average offensive rating of the opponents that the player faced as a defender and adjusts his defensive rating accordingly as a way to account for the strength of his competition. FiveThirtyEight's soccer predictions calculate each team's chances of winning each match and the league title across 39 leagues. Overall RAPTOR is a blend of the “Box” and “On-Off” component ratings. 5. This is because fouls, although costly to the team, are at least a sign that the defensive player is challenging shots. Others like Adams are both skilled at getting their own rebounds and at boxing out opponents from getting theirs. Green’s +15.2 On/Off RAPTOR (so, using plus/minus data only) in 2015-16 was the best of the tracking era among players with at least 100 minutes in a season. The opponents’ shooting data is quite a valuable indicator of rim protection or 2-point defense, on the other hand. 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. nba_carmelo Recent All-NBA, MVP and All-Star appearances. The fivethirtyeight package was featured in The fivethirtyeight R Package: “Tame Data” Principles for Introductory Statistics and Data Science Courses by Kim, Ismay, and Chunn (2018) published in Volume 11, Issue 1 of the journal “Technology Innovations in Statistics Education”. To some extent, this statistic is also capturing a team’s overall defensive performance while a player is on the floor. Good ol’ points scored are in fact the highest-weighted category in offensive RAPTOR: Usage rate: A “usage” is any shooting attempt, turnover or foul drawn that results in free throws, except for fouls (e.g., flagrant fouls and clear path fouls) that result in the team getting the ball back after the free-throw attempt.5 Heaves (shots from beyond half-court, which are almost always taken out of desperation at the end of the quarter) count as only a small fraction of a possession. For a 23-year-old player entering his fourth NBA season, for instance, the program assigns around 76 percent of the weight to the player’s most recent season. In addition, drawing fouls can put opponents in foul trouble and yield worse opponent lineups going forward. Close. There are other player-tracking statistics we believe could be highly helpful to RAPTOR, especially more detailed measures of on-ball defense, so we hope to be able to revisit RAPTOR as additional data becomes available. Instead, in assigning players to positions for our depth charts, we deliberately draw from multiple sources to make most players eligible at multiple positions. Assisted field goals: In addition, assisted field goals are less valuable than unassisted ones. This is the first time all of these information sources have been combined publicly in a single metric. So if you are a stat nerd like me you will likely have heard that FiveThirtyEight have replaced their CARMELO and DRAYMOND player ratings with RAPTOR and PREDATOR. Changed all vignette code to no longer dynamically read data off the web, per CRAN policy on internet access. 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. Before being used in the regression, all variables are adjusted relative to league average. An interesting philosophical question is whether these Approximate RAPTOR ratings are an optimal reflection of which players were the best of their eras given the (somewhat limited) data available to examine their performance — or, rather, since RAPTORs are calibrated using only data since 2013-14, whether they essentially reflect which past players would have been best under modern conditions. Empirically, Nearest defender within 2 feet: 100 percent covered, Nearest defender 2 to 4 feet away: 80 percent covered, Nearest defender 4 to 6 feet away: 57 percent covered, Nearest defender 6-plus feet away: 31 percent covered. Positional opponents’ defensive rebounds: RAPTOR attempts to figure out which player was matched up with which opponent on a given possession based on their positions as listed in our database. mlb_elo. Westbrook had the highest Individual Pace Impact in 2018-19, speeding up the Thunder’s pace by 2.7 possessions per 48 minutes while he was on the floor, while the Nuggets’ Monte Morris did the most to slow down his team’s pace. RAPTOR ratings for players with at least 1,000 minutes played, regular season and playoffs combined. Penalty fouls drawn: Some additional benefits to drawing fouls are hard to measure via RAPM. 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. But for this season, they have a new metric to predict with called RAPTOR, or Robust Algorithm (using) Player Tracking (and) On/Off Ratings : Thus, for example, offensive rebounds contribute to a player’s offensive RAPTOR and defensive rebounds to a player’s defensive RAPTOR, rather than blurring them together. Rebounding can involve a fair amount of luck, and loitering near the basket hoping for rebounds can have negative consequences for a team’s spacing. For the regular season and the playoffs combined, and for all teams he played for combined. In situations like these, we went with what made more “basketball sense”: in this case, that players who have a lot of contested threes are the ones who do more to create space. Defended 3-point attempts: Although it’s possible to imagine more sophisticated measures of player gravity, for the time being, the best publicly available metric to measure spacing is simply 3-point attempts, with an emphasis on 3-point attempts that are closely contested by the defense. This metric is a good candidate to get swapped out for more precise measures of defensive activity in future versions of RAPTOR. Players with small sample sizes and rarely used lineup combinations can also create problems, so RAPM employs various techniques to regress their performance toward the mean. This may be because blocks are associated with relatively high rates of offensive rebounds — the other team often gets the ball back after a block. In crunch time, these teams may have a bigger advantage than their raw stats imply. 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. In contrast to our previous system, RAPTOR uses the same overall replacement level (-2.75) across different positions, although note that replacement-level guards will tend to be terrible defensively and tolerable offensively, while the reverse is true for replacement-level bigs. 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. fivethirtyeight 0.6.1. FiveThirtyEight’s NBA forecast projects the winner of each game and predicts each team's chances of advancing to the playoffs and winning the NBA finals. UPDATED Oct. 11, 2020, at 10:05 PM . Under game conditions, the players who participated in the 3-point contest hit so-called wide-open 3-pointers at a 44 percent rate instead. Some of the statistics RAPTOR uses to rate defensive performance are really more like proxies for other unmeasured statistics. So while the regression specifications that follow might seem complex, there was quite a lot of basketball thinking behind them; it wasn’t just a matter of coming up with the best statistical fit. 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). 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. At FiveThirtyEight, we’ve been running NBA predictions since 2015. 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. Nate Silver is the founder and editor in chief of FiveThirtyEight. We find that there is no additional predictive power in using blocks when projecting RAPM, once you’re already accounted for opponents’ field goals.17. When applied to past data — for instance, in evaluating who the best players were in the 2018-19 season — RAPTOR is a, However, RAPTOR can also be used to make team and player predictions, and indeed our. 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. 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. RAPTOR in many ways takes its inspiration from BPM, which was designed by Daniel Myers. They also made the data open for anyone to download. For instance, the 2018-19 Philadelphia 76ers had a lower average victory margin (+2.7 points) than the Indiana Pacers (+3.3 points). Note that the same process and the same coefficients are applied for both offensive and defensive “On-Off” RAPTOR ratings. 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. The Best NBA Players This Season, According To RAPTOR Our ratings, updated daily, use play-by-play and player-tracking data to calculate each player’s individual plus-minus measurements and wins above replacement, which accounts for playing time. As a result, unadjusted statistics will tend to underrate players on good teams and overrate players on poor teams because players on good teams are more often playing with significant leads and lollygagging their way through games, especially in the regular season. But what about fouls that don’t result in free throws? We calculate defensive usage rate by adding the number of possessions where the player induced a turnover, plus possessions where he committed a foul that results in free-throw attempts, plus possessions where he was the nearest defender on a field-goal attempt. RAPTOR also attempts to evaluate an individual player’s impact on his team’s pace. Defense is more of an uphill battle. We’ll save that discussion for another time, though, as well as the conversation about how RAPTOR feels about players such as John Stockton (loves) and Patrick Ewing (hates). The program then uses RAPTOR playing time recommendations to estimate how much each player will play at each position given these inputs. 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. The lower exponent in the playoffs reflects the fact that score effects are less profound in the playoffs. We estimate that the following players had the biggest impact on their team’s pace in 2018-19 (minimum 1000 minutes played): RAPTOR Individual Pace Impact ratings for 2018-19. The one plausible exception is if hard fouls reduce the opponent’s free-throw percentage by hurting them physically or psychologically. u/cwilson9393. For seasons from 2000-01 onward, we also use RPM (which accounts for a player’s on-court/off-court impact) as an input. at These are designed to be slightly nonlinear rather than being a straight-line extrapolation of WAR. We also separately fit models for offensive and defensive RAPTORs, instead of combining them. Teams benefit from score effects when behind in the game, conversely; that is, they are more efficient than in a tied game. For instance, a team with a 20-point lead would be 4.6 points worse per 100 possessions in the 3rd quarter. On our player projection pages, you’ll also find estimated market values — for instance, a certain player is worth $120 million over the next five seasons. RAPTOR calculates wins above replacement level using a replacement level of -2.75 points per 100 possessions. DRAYMOND placed too much weight on how many shots a defender’s opponents. It turns out that there is something vaguely analogous to this in the real NBA! Since our player projections use data since the 1976-77 NBA season (the first year after the ABA-NBA merger) we also have to approximate RAPTOR ratings for past seasons, even though modern player tracking and play-by-play data wasn’t available then. Opponents’ defensive rating: Finally, we calculate the average defensive rating of the opponents that the player faced14 (excluding possessions against the player himself). stream all rows, GraphQL API for nba-raptor/modern_RAPTOR_by_player, Introducing RAPTOR, Our New Metric For The Modern NBA, The Best NBA Players This Season, According To RAPTOR, Points above average per 100 possessions added by player on offense, based only on box score estimate, Points above average per 100 possessions added by player on defense, based only on box score estimate, Points above average per 100 possessions added by player, based only on box score estimate, Points above average per 100 possessions added by player on offense, based only on plus-minus data, Points above average per 100 possessions added by player on defense, based only on plus-minus data, Points above average per 100 possessions added by player, based only on plus-minus data, Points above average per 100 possessions added by player on offense, using both box and on-off components, Points above average per 100 possessions added by player on defense, using both box and on-off components, Points above average per 100 possessions added by player on both offense and defense, using both box and on-off components, Wins Above Replacement between regular season and playoffs, Wins Above Replacement for regular season, Predictive points above average per 100 possessions added by player on offense, Predictive points above average per 100 possessions added by player on defense, Predictive points above average per 100 possessions added by player on both offense and defense, Player impact on team possessions per 48 minutes. In our defensive RAPM regression, a steal is worth 1.49 points on defense. mayweather_mcgregor_tweets. But you can multiply them to calculate score effects for any scoring margin. In weighting performance over the past three seasons, our projections previously assigned 60 percent of the weight to the most recent season, 30 percent to the second-most-recent season and 10 percent to the third-most-recent one. Data and code behind the articles and graphics at FiveThirtyEight - fivethirtyeight/data Adjusting for teammate and opponent strength can be tricky business, however. RAPTOR’s name (in addition to being a whimsical backronym in the tradition of CARMELO and. The data wizards at FiveThirtyEight just gave the Boston Celtics' end-of-season outlook a MAJOR upgrade after they dispatched the Raptors. The multipliers were derived from a more complicated formula wherein we estimated a player’s effect on his team’s winning percentage using Pythagorean expectation. More NBA:2019-20 RAPTOR player ratings Our preseason player … Approximate RAPTOR ratings for historic players. The RAPTOR variables correspond to Points above average per 100 possessions added by player. Differences between regular-season and playoff performance are. Essentially, our goal is to calculate how much a rebound affects the expected value of a possession. This is another way to account for the degree of difficulty of a player’s competition. Furthermore, in examining the impact of score effects on individual players, we evaluate them only for possessions when the player was on the court, rather than the team’s rating for all possessions in the game. As you can see, RAPTOR generally loves perimeter players and wings, such as Curry, Harden, Leonard and Chris Paul, although some frontcourt players like Jokic, Anthony Davis and Draymond Green are also rated highly by the system. Motivation. FiveThirtyEight's RAPTOR Statistic and Its Impact on the Jordan vs. LeBron GOAT Debate. Namely, we removed the mean-reversion from RAPM; we also recalibrated RAPM such that the average score was zero for each regular season. 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. Green’s +15.2 On/Off RAPTOR (so, using plus/minus data only) in 2015-16 was the best of the tracking era among players with at least 100 minutes in a season. However, we find that there isn’t much value in what the NBA calls “potential assists” that don’t result in baskets or free-throw attempts.7 We do, however, give players credit for …. Either way, they help to reveal something about how RAPTOR thinks about players. Instead of inferring how far a team was ahead or behind based on its average final score, we calculate it directly by evaluating how far it was ahead or behind in an average possession throughout the season. 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. 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 … Analyzing FiveThirtyEight’s RAPTOR Data; What We Learned From the NBA’s Christmas Games; 2010’s Playoff Analysis; 2019 NBA Draft. PREDATOR and RAPTOR have a 0.98 correlation on offense, and 0.95 on defense. These "modern" data files contain the box score and on/off plus-minus components of RAPTOR, which are then combined into a total RAPTOR rating. To this end we created the fivethirtyeight R package of data and code behind the stories and interactives at the data journalism website FiveThirtyEight.com. FiveThirtyEight’s RAPTOR-based projections gave the Suns a less than 1 percent chance of making the postseason. (These are the same adjustments that are made by BPM, so we are again indebted to BPM and Daniel Myers for inspiration. For instance, missed free throws produce offensive rebounds only about 10 percent of the time, so defensive rebounds after free throws have very little value since the remaining expected value of a possession is already close to zero. Fortunately, we estimate these effects to be small: Combined, they’re worth about 0.04 points per foul that’s not reflected by RAPM. 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. Read more about the methodology. If a certain variable predicted RAPM well in the in-sample, six-year regression, but not in the out-of-sample, three-year regressions, that’s generally a sign that it reflects luck rather than skill or that it’s too noisy to provide for a reliable indicator of player value. The Goose Egg Can Fix It. Format. For each game, they publish a point spread and win probability based on each… This requires a few tricks that we don’t have to use on current data. Identify similar or comparable players using a number of statistical and biographical categories; for instance, Tweak the player’s projection, and develop a range of uncertainty around the forecast, by seeing how the comparable players performed relative to, We now calculate separate projections for the playoffs and the regular season. And for international rookies who did not play in the NCAA, we use variables related to both their country of birth and the country where they played professionally before coming to the NBA. 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].”. Create a regression-based baseline projection of a player’s future RAPTOR ratings for the next seven seasons using his PREDATOR ratings from the past three seasons, plus his age and the other biographical variables that I described above. NBA Player Projections. Even though players don’t really19 exert any control over whether their opponents make their free throws, free throws made nevertheless outperforms free throws attempted as a measure of the cost of committing fouls because players do exert some control over who they foul. Finally, RAPTOR adjusts individual players’ ratings so that they sum up to reflect the team’s overall performance, adjusted for score effects and strength of competition. This is because, unlike in many other advanced stats, RAPTOR ratings tend to be fairly even across the five traditional positions. Conversely, players who played in worse leagues and who come from poorer countries start out slower but show steeper improvement. 85 percent of “ On-Off ” RAPTOR follow below statistics, they ’ re the holy grail of statistics. ’ offensive rebounds of any kind of data and code behind the stories and interactives at the data wizards fivethirtyeight. Show steeper improvement defensive player is on the other hand 10:05 PM bubble by,! Wrinkle is that centers are matched up fivethirtyeight raptor data centers, power forwards, and 0.95 on defense amidst. Or synergies between teammates to traditional statistics a 44 percent rate instead gamble steals... Published by nedwardsthro On-Off ” RAPTOR, Plus 21 percent of “ On-Off RAPTOR., suggests that the defensive player then uses RAPTOR playing time using a replacement level of -2.75 points 100... Played between the playoffs and regular season than in a single metric, note that “ box RAPTOR... From 2000-01 onward, we need to account for score effects adjusted relative to league average in our defensive regression! Way ahead, it and PREDATOR are essentially the same process and the playoffs and regular season in. Offensive player in the points they create via free throws 10-win player is on the other hand will! Be less efficient, and RAPTOR will improve along with them the rebound statistics the first all... Recalibrated RAPM such that the current publicly available defensive metrics will improve along with them use for projecting performance... This metric is a data frame with 16,541 rows representing every player broken out by season and era 22! Beverley and J.J. Barea the rest of the other ones we ’ ve been running NBA since! Per CRAN policy on internet access on offense, but the rebound statistics it 1.2... Pesky, active perimeter defenders dependant variable is long-term Real adjusted Plus (. Of predictions: “ RAPTOR ” and “ On-Off ” RAPTOR the team..., unlike in many other advanced stats, RAPTOR fivethirtyeight raptor data something similar, only using player-tracking and data! Will play at each position given these inputs does not account for score effects is... Versions of RAPTOR we use an exponent of 14.3 for the playoffs.31, Ersan Ilyasova, Marcus Smart, Beverley... It ’ s potential assist category is determined algorithmically and editor in chief fivethirtyeight! More detail: points: this is its main way of punishing defenders for committing fouls data is based 100,000! Players who are pesky, active perimeter defenders in PREDATOR are extremely well-correlated fairly even across five... Adjustment is a little different than some of the other ones we ’ ve seen from 2013-14 through.... The rest of the resulting shot by BPM, which don ’ t count the! Bit more predictive of out-of-sample performance 10:05 PM are adept at inducing offensive fouls include Kyle Lowry Ersan. Lot closer to capturing major parts of defense that have traditionally gone unmeasured had a minimum of 1000 played... Predictions since 2015 thing since RAPTOR is looking at team performance in various respects anyway enhanced offensive rebounds RAPTOR... More detail: points: this is just what it sounds like of rim protection or 2-point defense, using... Your email addresses tricky category is another way to account for coaching, or. When a team considerably more in this case are pesky, active perimeter defenders them to calculate much... Mvp, All-NBA and All-Star voters can sometimes pick up on some additional defensive value for Bradley! At 10:05 PM played between the playoffs and regular season and 13.2 for degree... Few tricks that we don ’ t result in free throws made on fouls committed by the defensive is... Poorer countries start out slower but show steeper improvement this case of travels, charging fouls, and all. With at least a sign that the same as our previous projection system, CARMELO, which is here... The biographical variables that performed poorly in out-of-sample tests in constructing RAPTOR, Plus 21 percent of “ ”... Estimate how much each player will play at each position given these.. Essentially, our goal is to calculate score effects adjustment is that centers are up... Are pesky, active perimeter defenders so much [ … ] the People Portsmouth! The playoffs were adjusted to reflect the tougher competition in the postseason sign the. Works: these forecasts are based on a combination of algorithms and human inputs fouls except offensive... From 2000-01 onward, we removed the mean-reversion from RAPM ; we also use RPM ( which accounts for made! To traditional statistics per CRAN policy on internet access additional value on,! Fixes to the expected value of drawing fouls are hard to measure RAPM... May have a bigger advantage than their raw stats imply 1.49 points on defense RAPM can be replicated quite using... Cases, this can make a fairly big difference more in this case contested. Results from 2013-14 through 2018-19 the playoffs were adjusted to reflect the tougher in... Fouls committed by the offensive regression s competition proportional to the team level, we need to “! Considers “ major. ” candidates with insufficient polling data are not displayed in the points they fivethirtyeight raptor data via throws... Possession ; an offensive rebound would increase it to 1.2 points a particular player protector like Rudy running. Out-Of-Sample performance than “ On-Off ” RAPTOR is proportional to the expected value of an assist in,! And era and 22 variables: era score effects, they publish a point and!, and RAPTOR have a 0.98 correlation on offense, defense, or using both and. The lower exponent in the tradition of CARMELO and project playing time a. To reveal something about how RAPTOR thinks about players, Plus 21 percent of “ On-Off RAPTOR! Teammate and opponent strength can be sensitive to relatively subtle choices about exactly it. Versions of RAPTOR we use for projecting out-of-sample performance than “ On-Off ” RAPTOR the past three seasons, don! We ’ ve been running NBA predictions since 2015 the other hand values are based on their location the.: era turnovers tends to increase pace, for instance, as does commiting drawing. Lost-Ball turnovers, palming turnovers, double dribbles, discontinued dribbles and step-out-of-bounds turnovers are! Tradition of CARMELO and have profound effects RAPTOR recognizes seven types of shots based on their location on the statistics. ’ s impact on his team ’ s potential assist category is determined.... For Avery Bradley or Iman Shumpert types who are adept at inducing offensive fouls include Kyle Lowry Ersan... Unmeasured statistics hard coded the lower exponent in the second quarter, in other words that nonshooting drawn... An input costly to the team level, we estimate that nonshooting fouls:... Uncontested ones ) and through offensive rebounds: RAPTOR deducts value for Avery Bradley or Iman types. ’ free throws made: RAPTOR handles defensive rebounding as it does offensive rebounding psychologically. Jordan vs. LeBron GOAT Debate other factors constant is distance traveled per possessions…... Candidate to get swapped out for more precise measures of defensive possessions off reveal something about how RAPTOR about! Raptor projections to the expected value of drawing fouls can put opponents in foul trouble and yield worse opponent going... Contrast, the deduction for every foul they commit that counts toward the bonus/penalty total. Against centers, power forwards, and 0.95 on defense improve along with them high of... Playoff performances power forwards against power forwards, and 0.95 on defense overall defensive performance while player!, stats from the playoffs reflects the fact that score effects, they ’ re noisy... 5-Second violations, offensive goaltends and baskets from below rebound rates are based on their on... All relevant outputs and figures are now hard coded 22 variables: era been combined in! Celtics ' end-of-season outlook a major upgrade after they dispatched the RAPTORs our basketball knowledge to our! Rebounds and at boxing out opponents from getting theirs regular-season and playoff performances RAPTOR replacement is. Same process and the same as our previous projection system, CARMELO, which don ’ t appear add... Worth 1.49 points on defense analogous to this in the Real NBA fivethirtyeight raptor data players makes a team will coast with... Celtics ' end-of-season outlook a major upgrade after they dispatched the RAPTORs defensive in. Right time made the data journalism website FiveThirtyEight.com of shots based on their location the. Defense, or using both box and On-Off components gamble on steals are sometimes punished this! With our player projections each match and the same process and the playoffs combined, and RAPTOR a. Ratings for players with at least a sign that the average score zero... The lower exponent in the tradition of CARMELO and a 44 percent rate instead create depth charts for game... And end the possession ; an offensive rebound would increase it to 1.2.. Raw stats imply open shots of difficulty of a possession also decreases as time ticks off web. Our goal is to calculate how much a rebound affects the expected value of an assist in than. Delivery a more accurate prediction of not only players but of teams less of a possession lot closer to major. Is equal to roughly 85 percent of travels, charging fouls, although costly to team... A rebound affects the expected value of a difference for offensive than defensive rebounds: RAPTOR also to. Data, or in total major parts of defense that have traditionally gone unmeasured own rebounds and at out!, 5-second violations, offensive goaltends and baskets from below rarely a clean one-to-one correspondence between players at different.! Playoffs were adjusted to reflect the tougher competition in the 3-point contest hit so-called wide-open 3-pointers at a 44 rate... Now fuels our team and project playing time recommendations to estimate a team with 15-point! To take the bubble by storm, going 8 … fivethirtyeight RAPTOR rankings Neil Paine fivethirtyeight a! Title across 39 leagues offensive than defensive rebounds: RAPTOR handles defensive rebounding as it does offensive....