Forecasting Legends: Building Classification Models to Predict MLB Hall of Famers (Part 5)
In Part 5 of this 7-part series, I examine the Hall of Fame prospects of MLB players (hitters only) after their first 15 seasons.
Welcome to part five of "Forecasting Legends: Building Classification Models to Predict MLB Hall of Famers." In this installment, I take a significant stride forward by delving deeper into a player's career, now considering their first 15 seasons. By harnessing the power of advanced classification models, I aim to unearth fresh insights that will further refine my ability to predict the path to the prestigious Hall of Fame.
For those who have been avidly following this captivating series or those who need a refresher on the previous articles, you can explore some of the past articles, each containing invaluable information about my methodology and unwavering dedication to forecasting the next generation of legendary players. Let's continue my quest to unravel the secrets behind the path to baseball immortality!
· First 15 Years
Model 5- First 15 Years
Results
Group 1 included 5,557 records while Group 2 consisted of 567 records. After partitioning Group 1, a new dataset of 2,953 records was created (158 of which were placed in the training dataset while 2,795 were placed in the validation set). This data was fed through a Logistic Regression classification model as it proved to be the most accurate model of all the ones that were tested. The training set produced an accuracy of 93.04% (147/158) while the validation set produced an accuracy of 94.38% (2,638/2,795). The area under the curve of the validation set is 0.98584.
Group 1
When predicting whether a player would make it into the Hall of Fame, this model does a better job of predicting those that ended up in the Hall of Fame (based on the validation set). Of the 80 players in Group 1 that are in the Hall of Fame, the model misclassified 4 of them (5.00% error rate).
An example of one of these misclassifications is Harold Baines. Over the first 15 years of his career, Baines produced a WAR of 30.0 (389th among players in Group 1). During this time, he posted a slash line of .288/.349/.461 to go along with 277 HRs and 1,198 RBIs. He also appeared in 5 All-Star Games and was awarded 1 Silver Slugger. At the time, this model suggested that he had a 30.12% chance of getting into the Hall of Fame. Over the last seven seasons of his career, he accumulated 8.7 WAR while posting a slash line of .293/.376/.477 and adding 107 HRs and 430 RBIs. At the conclusion of his 22-year career, Baines had a 95.07% chance of getting into the Hall of Fame (a 215.68% increase from when his 15th season ended). Baines first became eligible for the Hall of Fame in 2007 but he would not get elected after failing to accrue enough votes (the largest percentage of the vote he captured was 6.1% in his fourth year). However, Baines would get elected in 2019 via the “Today’s Game Era Committee.”
On the flip side, of the 2,715 players in Group 1 that are not in the Hall of Fame, 153 were misclassified (5.64%). One example is Rico Carty. In his first 15 seasons, he produced a WAR of 32.7 (T-343rd among players in Group 1) while posting a slash line of .299/.369/.464. He added 204 HRs and 890 RBIs. He also appeared in 1 All-Star Game and earned a Batting Title. At the time, this model suggested that he had a 76.80% chance of getting into the Hall of Fame. Carty called it a career after 15 seasons. His career had some interesting turns as he contracted tuberculosis, suffered a leg injury, complained about playing time, and much more. Unfortunately, Carty’s career numbers fall short of his Hall of Fame peers. Statistically, his best season was in 1970 (his seventh season) when he produced a slash line of .366/.454/.584 with 25 HRs and 101 RBIs. He finished 10th in MVP voting. At the conclusion of his career, Carty had a 30.36% chance of getting into the Hall of Fame (a 60.47% decrease from when his 15th season ended). Carty was first eligible for the Hall of Fame in 1985 but failed to receive enough votes to stay on the ballot the following year (0.3% of the vote).
Group 2
This model predicts that 76 players (13.40%) will make it into the Hall of Fame based on their first 15 seasons. An example of someone who is no longer active is Hanley Ramirez. In his first 15 seasons, he accumulated 38.0 WAR (T-50th among players in Group 2) while posting a slash line of .289/.360/.486 with 271 HRs and 917 RBIs. He was honored at 3 All-Star Games, earned 3 Silver Sluggers, and was awarded Rookie of the Year. This model suggested that he had a 68.27% chance of making it into the Hall of Fame at the time. Ramirez called it a career after 15 seasons as father time simply caught up to him faster than he expected. Statistically, his best season came in 2009 (his fifth season) when he posted a slash line of .342/.410/.543 with 24 HRs and 106 RBIs. He finished second in MVP voting. Currently, he has a 45.55% chance of getting into the Hall of Fame (a 33.28% decrease from the time his 15th season ended). Ramirez will first be eligible for the Hall of Fame in 2025.
An example of a player who is active is Evan Longoria (currently of the Arizona Diamondbacks). He completed his 15th season in 2022. He accumulated 58.1 WAR (15th among players in Group 2) to go along with a slash line of .265/.334/.472 in this time. He also added 331 HRs and 1,131 RBIs. In addition, he had the honor of being recognized at 3 All-Star Games and was awarded Rookie of the Year. This model suggested that Longoria had a 99.40% chance of getting into the Hall of Fame based on his first 15 seasons of work. If his career were to end today, he would have a 96.76% chance of getting into the Hall of Fame.
This model also predicts that 491 players (86.60%) will not make it into the Hall of Fame. One of those players who is no longer active is Victor Martinez. Through 15 seasons, Martinez accumulated 33.2 WAR (63rd among players in Group 2) with a slash line of .298/.364/.462. He added 237 HRs and 1,124 RBIs. He was also honored at 5 All-Star Games and was awarded 2 Silver Sluggers. At that point, this model gave Martinez a 37.90% chance of making it into the Hall of Fame. Martinez would call it a career after 16 seasons. Statistically, his best season came in 2014 (his 12th season) when he posted a slash line of .335/.409/.565 with 32 HRs and 103 RBIs. He would finish second in MVP voting. Currently, Martinez has a 44.07% chance of getting into the Hall of Fame (a 16.29% increase from when his 15th season ended). Martinez will first be eligible for the Hall of Fame in 2024.
HOF Probabilities from Year 5 to Year 15
As we witnessed in previous installments of this series, certain players embarked on a swift trajectory toward the Hall of Fame, while others encountered significant challenges in solidifying their presence in the major leagues. To gain a deeper understanding of the players who bolstered their chances of entering the Hall of Fame and those who faced hurdles along the way, I will analyze and compare their probabilities after five seasons to their probabilities after 15 seasons.
Risers
Over the course of his first five seasons, Carlos Delgado accumulated 2.3 WAR while posting a slash line of .253/.342/.486 with 67 HRs and 218 RBIs. His odds of getting into the Hall of Fame at this point were slim (8.93%). However, he began to find himself at the plate after struggling in his first few seasons. In his next ten seasons, Delgado accumulated 40.2 WAR while posting a slash line of .287/.396/.563 with 364 HRs and 1,156 RBIs. He was also recognized at 2 All-Star Games and was awarded 3 Silver Sluggers. At the conclusion of his 15th season, Delgado would have a 90.58% chance of getting into the Hall of Fame (a 914.38% increase from when his fifth season ended). At the conclusion of his 17-year career, Delgado had an 84.85% chance of getting into the Hall of Fame. Delgado first became eligible for the Hall of Fame in 2015 but failed to capture enough votes causing him to be removed from the ballot the following year (3.8% of the vote).
Fallers
Through his first five seasons, Bobby Bonilla accumulated 16.9 WAR while posting a slash line of .279/.350/.467 with 98 HRs and 426 RBIs. He was also honored at 3 All-Star Games and was awarded 2 Silver Sluggers. At this point, Bonilla had a 93.61% chance of getting into the Hall of Fame. In his next ten seasons, he accumulated 13.4 WAR while posting a slash line of .279/.362/.474 with 189 HRs and 747 RBIs. His odds of making it into the Hall of Fame were now at 24.11% (a 74.24% decrease from when his fifth season ended). At the conclusion of his 17-year career, Bonilla had a 51.08% chance of getting into the Hall of Fame. Bonilla first became eligible for the Hall of Fame in 2007 but failed to receive enough votes to stay on the ballot the following year (0.4% of the vote).