Abstract:

Researching student assessment data through the process of data mining is very intriguing. Applying data analytics and clustering algorithms to student assessment data allows one to further research and discover unknown patterns, trends and connections that would not otherwise be detected. Clustering data allows student assessment data to be grouped and allows key policy makers, administrators and school districts to make more informed, data-driven decisions within their schools.

The methodology chosen within this research is divided into six steps based on the data science process:
1) Frame the problem,
2) Collect the raw data needed for your problem.
3) Process the data for analysis,
4) Explore the data,
5) Perform in-depth analysis and
6) Communicate results of the analysis.

The student data clusters will be spilt into 5 groups to gain the performance characteristics of students: advanced, proficient, passing, basic and minimum. We will use 2000 student data and four variables from State Assessment courses in: English (English 2), History (U.S. History), Mathematics (Algebra 1), and Science (Biology 1) focusing on freshman, sophomore and junior level high school students in a public school district. We are employing various data analytics methods to assist in informing educators about the importance of using data in assessing student performances on the different metrics of measuring learning progressions and increase graduation rates in secondary education.

Keywords:

Education, student assessment, clustering algorithms, data analytics, data mining, big data, student data, secondary education, technology, research projects.