1. Data Mining Lab Student performance evaluation

2. Rate of learning varies from student to student May depend on similarity of the problem Is it possible to find out the knowledge requirment of one problem from the student performance data?

3. Task Description 5 data sets given. 3 development, 2 challenge data set Each comprise of training portion and a test portion Develope a learning model from the data set Use model to learn from data set And predict the student result

4. Data Format Data taken from student and computer- tutorial interaction Student solve the problem Each interaction is logged in as a transaction Four keys of the data are: Problem, Step, Knowledge-Component and oppurtunity

5. Example: A student is asked to solve a problem which is to find the area of a scraped metal left over after removing a circular area from a square.

6. Steps find the radius of the end of the can (a circle) find the length of the square find the area of the end of the can find the area of the square ABCD find the area of the left-over scrap

7. The whole collection of steps solves the problem. The student might also take hint Answer incorrectly Each hint request, incorrect attempt, or correct attempt is a transaction, and each recorded transaction

8. TABLE

9. Knowledge component Knowledge component is the piece of information that can help solve a problem Eg: Circle_area Square_area The oppurtinity count for a given Knowledge component of a student increases by 1, each time a student encounter the Knowledge component.

10. Actual Data Set These data sets come from multiple schools over multiple school years. The systems include the Carnegie Learning Algebra system, deployed 2005-2006 and 2006-2007, and the Bridge to Algebra system, deployed 2006-2007. Row: The row number Anon Student Id: An anonymus Id for each student Problem Hierarchy: Hierarchy of the curriculam level containing the problem Problem Name: Unique identifier for the problem Problem view: The total number of time student encounters the problem Step Name Step start time First Transaction time: The time of the first transaction toward the step

11. Correct Transaction Time: the time of the correct attempt toward the step Step End Time: the time of the last transaction toward the step. Correct Step Duration: The step duration if the first attempt for the step was correct. Error Step Duration: The step duration if the first attempt for the step was an error (incorrect attempt or hint request). Correct First Attempt: The tutor's evaluation of the student's first attempt on the step - 1 if correct, 0 if an error. Incorrect: Total number of incorrect attempts by the student on the step. Hints: Total number of hints requested by the student for the step. Corrects: Total correct attempts by the student for the step. (Only increases if the step is encountered more than once.)

12. Attribute to be estimated For the test portion of the challenge data sets, values will not be provided for the following columns: Step Start Time First Transaction Time Correct Transaction Time Step End Time Step Duration (sec) Correct Step Duration (sec) Error Step Duration (sec) Correct First Attempt Incorrects Hints Corrects

13. Splitting of the data

14. Why can it be useful? A good model can identify the underlying factor which makes a topic easy or difficult for the students. Can help in developing high quality curricula and lesson plans Can save a lot of time for students

15. Link http://www.sigkdd.org/kdd-cup-2010- student-performance-evaluation http://www.sigkdd.org/kdd-cup-2010- student-performance-evaluation