+ All Categories
Home > Documents > Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author:...

Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author:...

Date post: 01-Jan-2016
Category:
Upload: sandra-lucas
View: 218 times
Download: 0 times
Share this document with a friend
Popular Tags:
24
Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor : Dr. Jia-Ling Koh Speaker : Sheng-Chih Chu 1
Transcript
Page 1: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Predicting Student Risks Through Longitudinal Analysis

Date : 2015/04/23

Resource : KDD’14

Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala….

Advisor : Dr. Jia-Ling Koh

Speaker : Sheng-Chih Chu

1

Page 2: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Outline

• Introduction• Data Description & Defining Risk• Data Processing• Experiments• Conclusion

2

Page 3: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

IntroductionMotivation:

• K-12 reflects the most critical phase of an personal lifelong learning, during which the opportunities for a successful future need to be created and nurtured.

• Poor academic in K-12 is often precursor to unsatisfactory eduational outcomes,which are associated with social costs and significant personal.

3

Page 4: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

IntroductionMotivation:

4

Page 5: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Introduction

Goal:

• Building predictive module to predict students at risk of poor performance is first goal.

• In addition, early prediction can allow teachers take remedial actions in a students’s learning path.

5

Page 6: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Outline

• Introduction• Data Description & Defining Risk• Data Processing• Experiments• Conclusion

6

Page 7: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Data Description

• GCPS is one of the largest school systems in the US,consisting of 132 schools and serving more than168000 students at present.

7

Page 8: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Defining Risk

• CRCTs : (Score rang from 650~900)• 850↑(excedding standards)• 800 (standards)• 800↓(at risk)• (mathematics,science)

• ITBS : (provse PR)• 25% as a thresholds on grade 8 (at risk• (reading,written expression,mathematics,science,…)

• CogAt• (reasonable ability)

8

Page 9: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Outline

• Introduction• Data Description & Defining Risk• Data Processing• Experiments• Conclusion

9

Page 10: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Data Processing and Feature

10

Data warehouse

19 millionSPSS

Modeler

Consider CRCT,ITBS,CogAt

Page 11: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

CRCTs for grade7

Mike 750

Jasmine  

Thomas  

Alice 821

Peter  

Jenny 812

Longitudinal Feature Data

  

Grade CRCTs for grade8

CRCTs for grade7

CRCTs for grade6

CRCTs for grade5

ITBS for grade8

ITBS for grade5

ITBS for grade3

Mike 7   750 680 693   42 43Jasmine 6     823 805   62 58Thomas 5       725   45 42Alice 8 832 821 815 811 68 62 59Peter 4             64Jenny 7   812 795 822   60 63

11

Grade

Mike 7

Jasmine 6

Thomas 5

Alice 8

Peter 4

Jenny 7

CRCTs for grade8

Mike

Jasmine

Thomas

Alice 832

Peter

Jenny

Page 12: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Student Profile

12

  

gender ethnicity

Free meal

Gifted Special education

Absent day

Sus-pensions

Discipline

Mike M B Y N Y 0 X 85Jasmine F W N Y N 10 X 87Thomas M W N  N N 5 X 85Alice F W Y Y N 0 X 92Peter M W N N N 20 O 65Jenny F B N Y N 0 X 90

gender

Mike M

Jasmine F

Thomas M

Alice F

Peter M

Jenny F

ethnicity

Mike B

Jasmine W

Thomas W

Alice W

Peter W

Jenny B

Discipline

Mike 85

Jasmine 87

Thomas 85

Alice 92

Peter 65

Jenny 90

Page 13: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Merged Data Set

13

  

gender ethnicity

Free meal

Gifted Special education

Absent day

Sus-pensions

Discipline

Mike M B Y N Y 0 X 85Jasmine F W N Y N 10 X 87Thomas M W N  N N 5 X 85Alice F W Y Y N 0 X 92Bill M W N N N 20 O 65Jenny F B N Y N 0 X 90

  

Grade CRCTs for grade8

CRCTs for grade7

CRCTs for grade6

CRCTs for grade5

ITBS for grade8

ITBS for grade5

ITBS for grade3

Mike 7   750 680 693   42 43Jasmine 6     823 805   62 58Thomas 5       725   45 42Alice 8 832 821 815 811 68 62 59Peter 4             64Jenny 7   812 795 822   60 63

Page 14: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

• Target variable: CRCT grade 8

Creation of Target Variable Dependent Data

14

  

Grade CRCTs for grade8

CRCTs for grade7

CRCTs for grade6

CRCTs for grade5

ITBS for grade8

ITBS for grade5

ITBS for grade3

Mike 7   750 680 693   42 43Jasmine 6     823 805   62 58Thomas 5       725   45 42Alice 8 832 821 815 811 68 62 59Peter 4             64Jenny 7   812 795 822   60 63

Page 15: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Imputation of Missing Features

  

Grade CRCTs for grade8

CRCTs for grade7

CRCTs for grade6

CRCTs for grade5

ITBS for grade8

ITBS for grade5

ITBS for grade3

Mike 7   750 680 693   62 43Jasmine 6     823 805   58Thomas 5       725   65 42Alice 8 832 821 815 811 78 71 59Peter 4             64Jenny 7   812 795 822   72 63Jason 7 790 785 801 58 63Mao 7 635 697 45Marry 8 846 777 51 58Cube 8 545 657 732 39 47Bill 7 753 745 44 49Gary 8 897 902 87 91 96Han 8 801 786 759 70 54

15

Mean: (832+545+897+801)/4 = 769

Mean: (750+821+…+753+902)/8 = 788

Page 16: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Experiments

• Introduction• Data Description & Defining Risk• Data Processing• Experiments• Conclusion

16

Page 17: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Risk Prediction

17

Page 18: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Dataset

• ITBS data set contains 58361 samples containing 15.3% positive(at-risk) and 84.7% negative(non-risk)

• CRCT data set contains 43036 students containing 10.7% and 89.3% samples.

• Used 5-fold cross validation• Used SPSS or Weka

18

Page 19: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Peformance

19

Page 20: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Performance

20

Page 21: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Early Prediction of the Risk

21

Page 22: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Early Prediction of the Risk

22

Page 23: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Outline

• Introduction• Data Description & Defining Risk• Data Processing• Experiments• Conclusion

23

Page 24: Predicting Student Risks Through Longitudinal Analysis Date : 2015/04/23 Resource : KDD’14 Author: A.Tamhan,S.Ikbal,B.Sengupta,M.Duggirala…. Advisor :

Conclusion

• The result showed that a student’s risk of poor performance can be predicted with reasonable accuracy.

24


Recommended