Willamette+Athlete+Group

At this point in time there is very little research that has already been done about Division III recruiting and its accuracy. While doing research on the topic, our team struggled to find information pertaining to Division III sports recruiting in general. The majority of the articles that we found were merely explanatory articles about how the recruiting process works and how it has become more uniform among schools over time. All schools also have to comply with NCAA standards //[1]// //.
 * Data Mining Willamette Sports Recruitment **
 * Introduction **

One study did show that Division III recruiting had adopted the same methodology to recruiting as Division I schools and the inevitability of the evolution of the Division III recruiting process//[2]. More than anything, our group found one article that was written about the level of recruitment and how it is related to academics since Division III schools are not permitted to give sports scholarships //[3]// //. Schools have the ability to give academic scholarships to their athletes which might suede them into attending one school over another. It also discredits the recruiting system by saying that it is changing the culture of the schools in a negative way by letting too many under-qualified students into schools//[4]. Overall, the lack of research is not giving our team much to compare our study against, but also allows us to draw some of our own conclusions.

In order to become better informed on the recruiting process, we have conducted interviews with several coaches in the athletic department at Willamette University as to the current success in their efforts. The result is very mixed reviews. For example, the baseball coach has said that he would like to get a recruiting class of 15 to enroll this year. In order to do that he needs to have 60 kids admitted, which means 80 have to apply. In order to get the applicants he is currently dealing with an active recruiting list of 130-160 prospective students //[5]// //. It is successful if he gets the target number of kids but the real question is how effective or efficient is it. From the number perspective, it looks like a success rate of about 10%. Tennis//[6] and men’s soccer //[7]// //also do not think that their recruiting process is working as it should. On the other hand, there are programs at in the department that believe they are successful, such as football//[8], enrolling up to 50 prospects a year, and track and field //[9]// //, enrolling up to 100 prospects on their good years.

Another source for outside information was looking at the winning percentage over the last four years for the sports that keep track of win loss records//[10]. By looking at this information, it might provide us with another predictor for the success rate. While it is not exactly literature, it does paint a picture of where the different areas of the department currently stand. In order to use the data from the recruiting process here, the most important things for our group to consider is what we are using to define success for recruiting at Willamette University. Next, we need to look at the data in as many different ways as possible to see if the recruiting here is more successful in certain areas, such as by sport, ethnicity, sex, etc. It is important to see if the overall department is successful under our definition and then to look and see if there are factors contributing to that. ETHNICITY CODE 10, 11, 12 Asian American 20 African American 30 Native American 40-49 Hispanic American 50 Caucasian 60 Foreign Student (non U.S. citizen) 80 Other (they said something other than an ethnicity--things like Irish/Norwegian) 81 Multiracial 99 No info/unknown
 * Data **
 * Sport || Sport Played || Baseball, Soccer, Football, Crew, Golf, Basketball, Track, Cross Country, Swimming, Tennis ||
 * Rank || Rank Determined By Recruiter || 1,2, 3, 4 ||
 * Start Term || Term in Year Player Starts || 2004, 2005, 2006, 2007, 2008 ||
 * Fr/T || Freshman (Fr)/Transfer (T) || Fr, T ||
 * Application Status || Application Status || AD, AW, ND, WA, WW, WP, DF, MS, WB, BW, DW, DN, HD, IF, CP ||
 * Deposit || Deposit Paid || Y (Yes), N (No) ||
 * Name || Name of Player || Last Name, First Name ||
 * Ethnicity Code || Ethnicity of the Player || 10, 11, 12, 20, 30, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 60, 80, 81, 99 ||
 * Gender || Gender of the Player || M (Male), F (Female) ||

APPLICATION STATUSES AD Admitted Regular AW Admitted from the Waitlist ND Admitted Non-degree WA Withdrawn Admitted WW Withdrawn from the Waitlist after being admitted WP Withdrawn deposited student DF Deferred (withdrawn with the intention of coming in a later year) MS Moved to Student (admitted, paid and enrolling) WB Withdrawn before decision (regular) BW Withdrawn before decision (Waitlist) DW Denied from the Waitlist DN Denied Regular HD Hold for additional info IF Incomplete file CP Complete File The first step will take is data transformation. The data source we have been provided has the name of the sport the individual is being recruiting for and their ranking. To separate these two distinct pieces of data we will deploy a series of derive nodes. Each derive node contains “if then else if” statements. Each node will create a column named for the sport and ranking (i.e. “basketball_rank”). After a column for every sport has been created we will use a derive node to combine these columns into a single column named rank. After the rank has been separated from the name we will then create a derive node using “if then else if” statements to separate the sport name into its own column. After this has been done we will filter the redundant fields of “name_and_rank” and “@FIELD_rank”.
 * Procedure **

We also will be creating a new column for the win percentage for the team the individual was recruited for four years for freshmen and x years for transfer students. The final change that we made to the data was to simplify the admittance codes from 15 to 3; admitted, enrolled, and denied. After we have made these changes to the data we will not need to make any attempt at normalizing the data, since it is purely categorical.

Because of the categorical nature of the data we feel there are several types of models that would be most effective. The three models we are planning on using are clustering, market basket, and neural network. We are also considering a logistical regression, since out output variable has been limited to three choices.

In order to better understand our data we will run our information through different Clementine Models and study the output from these individual models. Most of the data we have attained is categorical data because it is information collected on students who were being recruited by Willamette University. We will however also use the win-lose records from specific sports in order to better understand if the recruiting was successful. With this information we will try to determine whether good recruiting years and good sports records are correlated and if so we will be able to help Willamette university better recruit. Since some of the recruits are from recent years, we may be able to analyze their personal performance to see what determines a top performing athlete
 * Data Interpretation **

The purpose of this project is to determine the efficiency of the athletic recruiting process at Willamette University. Since athletics play an important role at attracting new students, developing a winning team will increase the notoriety of the school. There has not been much research into this area in the past and the current data set does not allow for a full analysis, so we will focus our efforts on determining if the recruiting is effective and how it can be improved from the information given to us. In our clustering method we hope to build a model that will show us the students which want to come to this school and from which ranking. Using market basket analysis we hope to derive the major contributing factors to what people accept their offers. And we will use neural nets as a comparison to the other methods.
 * Purpose and Goals **

//[1]// //NCAA Official Website: [|www.ncaa.org]. Accessed March 2009.// //[2]// Tobin, Eugene M., Fall 2005, Vol. 85 No. 3, Athletics in Division III Institutions: Trends and Concerns. //[3]// //Athletic Scholarships: [|www.athleticscholarships.net/sports-scholarship.htm]. Accessed March 2009.// //[4]// Tobin, Eugene M., Fall 2005, Vol. 85 No. 3, Athletics in Division III Institutions: Trends and Concerns. //[5]// //Swick, Aaron. Willamette University Head Baseball Coach. Interview. February 12, 2009// //[6]// Roberts, Becky. Willamette University Tennis Coach. Interview. March 10, 2009 //[7]// //Larson, Nelson. Willamette University Men’s Soccer Coach. Interview. February 18, 2009// //[8]// Cass, Tony. Willamette University Head Recruiter, Assistant Football Coach. March 12, 2009 //[9]// //McGuirk, Matt. Willamette University Head Track and Field Coach. February 3, 2009// //[10]// McKinney, Robert. Team Sports, Statistics. Willamette.edu/athletics. April 13, 2009

- Kody Betonte, Mike Bowers, Elizaberth Gilgan, Ken Beatty, Kyle McGeeney