College Football Recruiting Prediction Model

College Football Recruiting Prediction Model

Predictions for the Top Uncommitted Recruits as of February 08, 2008

Welcome to the “college football recruiting prediction model” website hosted by the Stetson School of Business and Economics at Mercer University. This website contains information about an econometric model that has been developed by three economists (Mike DuMond, Allen Lynch and Jennifer Platania) to predict the collegiate choices of high school football players.

Each year, on the first Wednesday in February, college coaches, administrators, and football fans eagerly await the choices of high school seniors as they sign “letters of intent” with specific colleges. These letters of intent officially link top ranked high school football players with specific colleges and effectively determine the rosters of college football programs in years to come. The process of recruiting these players is highly competitive, as schools battle with one another to sign the best of the best in the world of high school football. Recruiting gurus attempt to forecast the choices of these high school athletes as college football fans desperately search the Internet for bits and pieces of information that might shed light on the choices of these teenage football players.

The importance to a specific college of signing a strong group of athletes on “signing day” cannot be overstated. College football has become big business in recent years. The amount of revenue a college or university can generate by fielding a competitive football team can reach staggering levels. The college football program at the University of Texas at Austin, for example, brought in over $53 million[1] during the 2004-2005 academic year. Given the potential for such revenue, as well as the general interest in the sport held by rabid college football fans, an econometric model to predict the choices of college becomes useful.

The authors used statistical software developed by SAS along with data provided by Rivals.com (a national website dedicated to college football and recruiting) in the development of this model. The model was built on a database capturing characteristics and decisions of 3,395 recruited athletes for the three “recruiting seasons” between 2002 and 2004. On average, each player was choosing from among a group of 4 schools. A wide array of player and team level data were gathered for this task. Then, a special form of a probit model was developed to capture, to the best extent possible a statistical equation to capture the decision making process.

We were a bit surprised by the results. There were a number of factors that we thought would significantly impact the decision of the high school athlete that didn’t. For example, factors like the school’s graduation rate, the number of Bowl Championship Series (BCS) bowl appearances, the current roster depth at the recruited player’s position, the number of players from a specific college drafted by the NFL, and even the number of national championships won by a particular program don’t systematically influence the decisions of high school athletes. Surprised? So were we. What, then, does matter? As it turns out the following factors DO significantly impact the decision of high school athletes:

Whether the athlete made an “official visit” to a specific college

Whether the school is in a BCS conference

The distance from the high school athlete’s hometown to a specific school

Whether the recruit is in the same state as a specific school

The final AP Ranking of a specific school in the previous year of competition

The number of conference titles a school has recorded in recent years

Whether the school is currently under a “bowl ban” for violating NCAA rules

The current number of scholarship reductions a school faces for violating NCAA rules

The size of the team’s stadium (measured in terms of seating capacity)

Whether the school has an on-campus stadium

The current age of the team’s stadium

So, in a nutshell, high school athletes prefer winning programs that are
close to home, are in possession of good physical facilities, and are in good
graces with the NCAA. Interestingly enough however, reduced scholarships increase the likelihood of choosing a particular school, holding all else constant. This is likely because reduced scholarships imply reduced competition for exposure and playing time in the future.

Does the model predict accurately? We believe the model predicts quite accurately! Within the sample used to build the model, we accurately predicted approximately 68 percent of the choices of high school athletes. (Considering that each player was choosing from a group of, on average, four schools, a 68 percent accuracy rate isn’t too bad.) In 2005, we examined the choices of the top 100 high school prospects and used the model to accurately predict the choices of 71 of these players. After a brief hiatus in 2006 we came back with more predictions in 2007. For the top 100 of the 2007 recruiting class, the model accurately predicted the decisions of 72. Making the accuracy rate of the 2007 class more impressive is the fact that each player in the 2007 class was choosing from an average of 6.2 schools!

Information regarding the predicted and actual choices for the top 250 recruits of 2008 (as determined by Rivals.com) appears to the right. Also to the right, the potential schools and associated probabilities, as determined by the results of the model, for the recruits in this group that have yet to decide are listed.

The results of this model appear in an article published in the February, 2008 edition of The Journal of Sports Economics. The recruiting prediction model is the subject of a current article authored by Andy Staples in Sports Illustrated (link). Additionally, separate media stories regarding the results of the model have appeared in the Columbus Dispatch, the Atlanta Journal-Constitution and via an Associated Press article written by Paul Nowell in 2005.

The authors thank Juan Del Valle for his invaluable assistance in the collection of GIS related data. The authors would also like to thank Kaitlin David for web site development and support.

About the authors:

Mike DuMond is an Economist with ERS Group, Inc. in Tallahassee, FL; Allen K. Lynch is Associate Professor of Economics and Quantitative Methods in the Stetson School of Business and Economics at Mercer University; and Jennifer Platania is Assistant Professor of Economics at Elon University.

Click here for a list of Predictions for the Committed Players

Currently, the model is predicting at a 73% accuracy rate for the committed players.

Player Rank

Player Name

Possible School

Estimated Probability

1 Terrelle Pryor* Penn State 35.9%

Ohio State 23.8%

Michigan 22.7%

Oregon 8.4%

Pittsburgh 5.4%

Florida 2.0%

LSU 1.8%

* Terrelle Pryor's predictions assume an official visit to both Penn State and Oregon.

Predictions for the Top Committed Recruits as of February 08, 2008

Model is currently predicting correctly for 73% of these players,

assuming the recruits abide by their public commitments.

Player Rank

Player Name

Predicted School

Committed To:

Match?

2 DaQuan Bowers Clemson Clemson Yes

3 Mike Adams Ohio State Ohio State Yes

4 Julio Jones Alabama Alabama Yes

5 Patrick Johnson Florida LSU No

6 Darrell Scott Texas Colorado No

7 Marcus Forston Tennessee Miami (FL) No

8 Baker Steinkuhler Nebraska Nebraska Yes

9 A.J. Green Georgia Georgia Yes

10 Will Hill Florida Florida Yes

11 Matt Kalil Southern Cal Southern Cal Yes

12 Michael Brewster Ohio State Ohio State Yes

13 R.J. Washington Oklahoma Oklahoma Yes

14 Blaine Gabbert Missouri Missouri Yes

15 Tyron Smith Southern Cal Southern Cal Yes

16 Nigel Bradham Florida State Florida State Yes

17 Omar Hunter Florida Florida Yes

18 Matt Patchan Florida Florida Yes

19 Jermie Calhoun Oklahoma Oklahoma Yes

20 Kyle Rudolph Ohio State Notre Dame No

21 DeVier Posey Ohio State Ohio State Yes

22 DeAndre Brown LSU Southern Miss No

23 Arthur Brown LSU Miami (FL) No

24 Richard Samuel Georgia Georgia Yes

25 Dayne Crist Southern Cal Notre Dame No

26 Jonathan Baldwin Pittsburgh Pittsburgh Yes

27 Michael Floyd Notre Dame Notre Dame Yes

28 Burton Scott Auburn Alabama No

29 Stephen Good Oklahoma Oklahoma Yes

30 Tyler Love Alabama Alabama Yes

31 Blake Ayles Southern Cal Southern Cal Yes

32 Ethan Johnson Notre Dame Notre Dame Yes

33 Lamaar Thomas Maryland Ohio State No

34 Jerrell Harris Auburn Alabama No

35 Alonzo Lawrence Hawaii Alabama No

36 Aaron Williams Texas Texas Yes

37 Trevor Robinson Notre Dame Notre Dame Yes

38 Brandon Harris Florida Miami (FL) No

39 Lucas Nix Pittsburgh Pittsburgh Yes

40 Wes Horton Southern Cal Southern Cal Yes

41 Darryl Stonum Michigan Michigan Yes

42 Armond Armstead Southern Cal Southern Cal Yes

43 E.J. Manuel Florida State Florida State Yes

44 Boubacar Cissoko Michigan Michigan Yes

45 DeAngelo Tyson Georgia Georgia Yes

46 Etienne Sabino Southern Cal Ohio State No

47 Ryan Williams Virginia Tech Virginia Tech Yes

48 D.J. Monroe Texas Texas Yes

49 Dann O'Neill Michigan Michigan Yes

50 Jarvis Humphrey Texas Texas Yes

51 Janoris Jenkins Florida Florida Yes

52 Jameel Owens Oklahoma Oklahoma Yes

53 DeSean Hales Texas Texas Yes

54 A.J. Harmon Georgia Georgia Yes

55 Mark Barron Auburn Alabama No

56 Nick Perry Michigan Southern Cal No

57 Kavario Middleton Washington Washington Yes

58 Aldarius Johnson Miami (FL) Miami (FL) Yes

59 Mike Glennon N.C. State N.C. State Yes

60 Barrett Jones Florida Alabama No

61 Ramon Buchanan Florida Miami (FL) No

62 Lynn Katoa Oklahoma Colorado No

63 Aaron Hester UCLA UCLA Yes

64 Garrett Goebel Illinois Ohio State No

65 Marcus Robinson Miami (FL) Miami (FL) Yes

66 Devoe Torrence Ohio State Ohio State Yes

67 Jordan Futch Miami (FL) Miami (FL) Yes

68 Andrew Luck Stanford Stanford Yes

69 Joshua Jarboe Oklahoma Oklahoma Yes

70 Chris Tolliver LSU LSU Yes

71 Rahim Moore UCLA UCLA Yes

72 Jonas Gray Notre Dame Notre Dame Yes

73 Brendan Beal Boston College Florida No

74 Ryan Baker Florida State LSU No

75 Jarmon Fortson Auburn Florida State No

76 Jeff Fuller Texas A&M Texas A&M Yes

77 Gerell Robinson Arizona State Arizona State Yes

78 Cyrus Gray Texas A&M Texas A&M Yes

79 Brice Butler Southern Cal Southern Cal Yes

80 Corey Liuget Miami (FL) Illinois No

81 Brandon Beachum West Virginia Penn State No

82 T.J. Bryant Florida Southern Cal No

83 William Green Auburn Florida No

84 Tommy Streeter Miami (FL) Miami (FL) Yes

85 Toby Jackson Georgia Georgia Yes

86 Stacey McGee Oklahoma Oklahoma Yes

87 J.B. Shugarts Ohio State Ohio State Yes

88 Tavarres King Georgia Georgia Yes

89 Darius Fleming Notre Dame Notre Dame Yes

90 Joseph Ibiloye Oklahoma Oklahoma Yes

91 Ryan Bass Arizona State Arizona State Yes

92 Brandon Taylor LSU LSU Yes

93 Derrick Hall Texas A&M Texas A&M Yes

94 De'Anthony Curtis Arkansas Arkansas Yes

95 Dan Buckner Texas Texas Yes

96 D.J. Shoemate Southern Cal Southern Cal Yes

97 Uona Kavienga Southern Cal Southern Cal Yes

98 Bryce Givens Colorado Colorado Yes

99 Kemonte Bateman Arizona State Arizona State Yes

100 Nick Moody Florida State Florida State Yes

101 Cornelius Washington

	Predictions for the Top Uncommitted Recruits as of February 08, 2008
Welcome to the “college football recruiting prediction model” website hosted by the Stetson School of Business and Economics at Mercer University. This website contains information about an econometric model that has been developed by three economists (Mike DuMond, Allen Lynch and Jennifer Platania) to predict the collegiate choices of high school football players. Each year, on the first Wednesday in February, college coaches, administrators, and football fans eagerly await the choices of high school seniors as they sign “letters of intent” with specific colleges. These letters of intent officially link top ranked high school football players with specific colleges and effectively determine the rosters of college football programs in years to come. The process of recruiting these players is highly competitive, as schools battle with one another to sign the best of the best in the world of high school football. Recruiting gurus attempt to forecast the choices of these high school athletes as college football fans desperately search the Internet for bits and pieces of information that might shed light on the choices of these teenage football players. The importance to a specific college of signing a strong group of athletes on “signing day” cannot be overstated. College football has become big business in recent years. The amount of revenue a college or university can generate by fielding a competitive football team can reach staggering levels. The college football program at the University of Texas at Austin, for example, brought in over $53 million[1] during the 2004-2005 academic year. Given the potential for such revenue, as well as the general interest in the sport held by rabid college football fans, an econometric model to predict the choices of college becomes useful. The authors used statistical software developed by SAS along with data provided by Rivals.com (a national website dedicated to college football and recruiting) in the development of this model. The model was built on a database capturing characteristics and decisions of 3,395 recruited athletes for the three “recruiting seasons” between 2002 and 2004. On average, each player was choosing from among a group of 4 schools. A wide array of player and team level data were gathered for this task. Then, a special form of a probit model was developed to capture, to the best extent possible a statistical equation to capture the decision making process. We were a bit surprised by the results. There were a number of factors that we thought would significantly impact the decision of the high school athlete that didn’t. For example, factors like the school’s graduation rate, the number of Bowl Championship Series (BCS) bowl appearances, the current roster depth at the recruited player’s position, the number of players from a specific college drafted by the NFL, and even the number of national championships won by a particular program don’t systematically influence the decisions of high school athletes. Surprised? So were we. What, then, does matter? As it turns out the following factors DO significantly impact the decision of high school athletes: Whether the athlete made an “official visit” to a specific college Whether the school is in a BCS conference The distance from the high school athlete’s hometown to a specific school Whether the recruit is in the same state as a specific school The final AP Ranking of a specific school in the previous year of competition The number of conference titles a school has recorded in recent years Whether the school is currently under a “bowl ban” for violating NCAA rules The current number of scholarship reductions a school faces for violating NCAA rules The size of the team’s stadium (measured in terms of seating capacity) Whether the school has an on-campus stadium The current age of the team’s stadium So, in a nutshell, high school athletes prefer winning programs that are close to home, are in possession of good physical facilities, and are in good graces with the NCAA. Interestingly enough however, reduced scholarships increase the likelihood of choosing a particular school, holding all else constant. This is likely because reduced scholarships imply reduced competition for exposure and playing time in the future. Does the model predict accurately? We believe the model predicts quite accurately! Within the sample used to build the model, we accurately predicted approximately 68 percent of the choices of high school athletes. (Considering that each player was choosing from a group of, on average, four schools, a 68 percent accuracy rate isn’t too bad.) In 2005, we examined the choices of the top 100 high school prospects and used the model to accurately predict the choices of 71 of these players. After a brief hiatus in 2006 we came back with more predictions in 2007. For the top 100 of the 2007 recruiting class, the model accurately predicted the decisions of 72. Making the accuracy rate of the 2007 class more impressive is the fact that each player in the 2007 class was choosing from an average of 6.2 schools! Information regarding the predicted and actual choices for the top 250 recruits of 2008 (as determined by Rivals.com) appears to the right. Also to the right, the potential schools and associated probabilities, as determined by the results of the model, for the recruits in this group that have yet to decide are listed. The results of this model appear in an article published in the February, 2008 edition of The Journal of Sports Economics. The recruiting prediction model is the subject of a current article authored by Andy Staples in Sports Illustrated (link). Additionally, separate media stories regarding the results of the model have appeared in the Columbus Dispatch, the Atlanta Journal-Constitution and via an Associated Press article written by Paul Nowell in 2005. The authors thank Juan Del Valle for his invaluable assistance in the collection of GIS related data. The authors would also like to thank Kaitlin David for web site development and support. About the authors: Mike DuMond is an Economist with ERS Group, Inc. in Tallahassee, FL; Allen K. Lynch is Associate Professor of Economics and Quantitative Methods in the Stetson School of Business and Economics at Mercer University; and Jennifer Platania is Assistant Professor of Economics at Elon University.	Click here for a list of Predictions for the Committed Players Currently, the model is predicting at a 73% accuracy rate for the committed players.
	Player Rank	Player Name	Possible School	Estimated Probability
	1	Terrelle Pryor*	Penn State	35.9%
			Ohio State	23.8%
			Michigan	22.7%
			Oregon	8.4%
			Pittsburgh	5.4%
			Florida	2.0%
			LSU	1.8%
	* Terrelle Pryor's predictions assume an official visit to both Penn State and Oregon.
	Predictions for the Top Committed Recruits as of February 08, 2008
	Model is currently predicting correctly for 73% of these players, assuming the recruits abide by their public commitments.
	Player Rank	Player Name	Predicted School	Committed To:	Match?
	2	DaQuan Bowers	Clemson	Clemson	Yes
	3	Mike Adams	Ohio State	Ohio State	Yes
	4	Julio Jones	Alabama	Alabama	Yes
	5	Patrick Johnson	Florida	LSU	No
	6	Darrell Scott	Texas	Colorado	No
	7	Marcus Forston	Tennessee	Miami (FL)	No
	8	Baker Steinkuhler	Nebraska	Nebraska	Yes
	9	A.J. Green	Georgia	Georgia	Yes
	10	Will Hill	Florida	Florida	Yes
	11	Matt Kalil	Southern Cal	Southern Cal	Yes
	12	Michael Brewster	Ohio State	Ohio State	Yes
	13	R.J. Washington	Oklahoma	Oklahoma	Yes
	14	Blaine Gabbert	Missouri	Missouri	Yes
	15	Tyron Smith	Southern Cal	Southern Cal	Yes
	16	Nigel Bradham	Florida State	Florida State	Yes
	17	Omar Hunter	Florida	Florida	Yes
	18	Matt Patchan	Florida	Florida	Yes
	19	Jermie Calhoun	Oklahoma	Oklahoma	Yes
	20	Kyle Rudolph	Ohio State	Notre Dame	No
	21	DeVier Posey	Ohio State	Ohio State	Yes
	22	DeAndre Brown	LSU	Southern Miss	No
	23	Arthur Brown	LSU	Miami (FL)	No
	24	Richard Samuel	Georgia	Georgia	Yes
	25	Dayne Crist	Southern Cal	Notre Dame	No
	26	Jonathan Baldwin	Pittsburgh	Pittsburgh	Yes
	27	Michael Floyd	Notre Dame	Notre Dame	Yes
	28	Burton Scott	Auburn	Alabama	No
	29	Stephen Good	Oklahoma	Oklahoma	Yes
	30	Tyler Love	Alabama	Alabama	Yes
	31	Blake Ayles	Southern Cal	Southern Cal	Yes
	32	Ethan Johnson	Notre Dame	Notre Dame	Yes
	33	Lamaar Thomas	Maryland	Ohio State	No
	34	Jerrell Harris	Auburn	Alabama	No
	35	Alonzo Lawrence	Hawaii	Alabama	No
	36	Aaron Williams	Texas	Texas	Yes
	37	Trevor Robinson	Notre Dame	Notre Dame	Yes
	38	Brandon Harris	Florida	Miami (FL)	No
	39	Lucas Nix	Pittsburgh	Pittsburgh	Yes
	40	Wes Horton	Southern Cal	Southern Cal	Yes
	41	Darryl Stonum	Michigan	Michigan	Yes
	42	Armond Armstead	Southern Cal	Southern Cal	Yes
	43	E.J. Manuel	Florida State	Florida State	Yes
	44	Boubacar Cissoko	Michigan	Michigan	Yes
	45	DeAngelo Tyson	Georgia	Georgia	Yes
	46	Etienne Sabino	Southern Cal	Ohio State	No
	47	Ryan Williams	Virginia Tech	Virginia Tech	Yes
	48	D.J. Monroe	Texas	Texas	Yes
	49	Dann O'Neill	Michigan	Michigan	Yes
	50	Jarvis Humphrey	Texas	Texas	Yes
	51	Janoris Jenkins	Florida	Florida	Yes
	52	Jameel Owens	Oklahoma	Oklahoma	Yes
53	DeSean Hales	Texas	Texas	Yes
54	A.J. Harmon	Georgia	Georgia	Yes
55	Mark Barron	Auburn	Alabama	No
56	Nick Perry	Michigan	Southern Cal	No
57	Kavario Middleton	Washington	Washington	Yes
58	Aldarius Johnson	Miami (FL)	Miami (FL)	Yes
59	Mike Glennon	N.C. State	N.C. State	Yes
60	Barrett Jones	Florida	Alabama	No
61	Ramon Buchanan	Florida	Miami (FL)	No
62	Lynn Katoa	Oklahoma	Colorado	No
63	Aaron Hester	UCLA	UCLA	Yes
64	Garrett Goebel	Illinois	Ohio State	No
65	Marcus Robinson	Miami (FL)	Miami (FL)	Yes
66	Devoe Torrence	Ohio State	Ohio State	Yes
67	Jordan Futch	Miami (FL)	Miami (FL)	Yes
68	Andrew Luck	Stanford	Stanford	Yes
69	Joshua Jarboe	Oklahoma	Oklahoma	Yes
70	Chris Tolliver	LSU	LSU	Yes
71	Rahim Moore	UCLA	UCLA	Yes
72	Jonas Gray	Notre Dame	Notre Dame	Yes
73	Brendan Beal	Boston College	Florida	No
74	Ryan Baker	Florida State	LSU	No
75	Jarmon Fortson	Auburn	Florida State	No
76	Jeff Fuller	Texas A&M	Texas A&M	Yes
77	Gerell Robinson	Arizona State	Arizona State	Yes
78	Cyrus Gray	Texas A&M	Texas A&M	Yes
79	Brice Butler	Southern Cal	Southern Cal	Yes
80	Corey Liuget	Miami (FL)	Illinois	No
81	Brandon Beachum	West Virginia	Penn State	No
82	T.J. Bryant	Florida	Southern Cal	No
83	William Green	Auburn	Florida	No
84	Tommy Streeter	Miami (FL)	Miami (FL)	Yes
85	Toby Jackson	Georgia	Georgia	Yes
86	Stacey McGee	Oklahoma	Oklahoma	Yes
87	J.B. Shugarts	Ohio State	Ohio State	Yes
88	Tavarres King	Georgia	Georgia	Yes
89	Darius Fleming	Notre Dame	Notre Dame	Yes
90	Joseph Ibiloye	Oklahoma	Oklahoma	Yes
91	Ryan Bass	Arizona State	Arizona State	Yes
92	Brandon Taylor	LSU	LSU	Yes
93	Derrick Hall	Texas A&M	Texas A&M	Yes
94	De'Anthony Curtis	Arkansas	Arkansas	Yes
95	Dan Buckner	Texas	Texas	Yes
96	D.J. Shoemate	Southern Cal	Southern Cal	Yes
97	Uona Kavienga	Southern Cal	Southern Cal	Yes
98	Bryce Givens	Colorado	Colorado	Yes
99	Kemonte Bateman	Arizona State	Arizona State	Yes
100	Nick Moody	Florida State	Florida State	Yes
101	Cornelius Washington