1. Contraceptive Method Choice 指導教授 黃三益博士 組員 :B924020007 王俐文 B924020009 謝孟凌 B924020014 陳怡珺

2. Background and Motivation Population of the world increases tremendously, people of present day pay more attention to contraceptive method.

3. Step one: Translate the Business Problem into a Data Mining Problem Topic: Contraceptive Method Choice Predict the current contraceptive method choice (no use, long-term methods, or short-term methods) of a woman based on her demographic and socio- economic characteristics. Especially what kind of couples would chose long- term method.

4. Step two: Select Appropriate Data Title: Contraceptive Method Choice Sources:  Origin: Subset of the 1987 National Indonesia Contraceptive Prevalence Survey  Creator: Tjen-Sien Lim  Date: June 7, 1997

5. Step two: Select Appropriate Data Number of Instances: 1473 There is no missing value in this dataset.

6. Step two: Select Appropriate Data Number of attributes: 10 (including the class attribute) Wife's age Wife's education Husband's education Number of children ever born Wife's religion Wife's now working? Husband's occupation Standard-of-living index Media exposure Contraceptive method used (class attribute)

7. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Contraceptive method used class attribute1=No-use 2=Long-term 3=Short-term

8. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Wife's ageNumerical

9. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Wife's educationCategorical1=low 2, 3, 4=high

10. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Husband's educationCategorical1=low 2, 3, 4=high

11. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Number of children ever born Numerical

12. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Wife's religionBinary0=Non-Islam 1=Islam

13. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Wife's now working?Binary0=Yes 1=No

14. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Husband's occupationCategorical1, 2, 3, 4

15. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Standard-of-living indexCategorical1=low 2, 3, 4=high

16. Step three: Get to Know the Data Attribute Information Attribute NameAttribute TypeDescription of Attribute Value Media exposureBinary0=Good 1=Not good

17. Step Four : Create a Model Set Raw Data

18. Step Four : Create a Model Set Total 1473 samples 75% of the data as training set the rest of the data as testing set →By random sampling Rapid Miner

19. Step Five: Fix Problems with the Data No missing value Skewed distributions

20. Step Six : Transform Data to Bring Information to the Surface most of the values of the attribute named Media Exposure are “Good” the numeric variables to do the statistical analysis to finding outliers

21. Step7 Build Model By RapidMiner, build it with Decision Tree

22. Step7 Build Model(con’t)

23. Ripper Rule if wife_age > 30 and Num_children_born <= 1 then 1 (53 / 1 / 3) if Num_children_born <= 0 then 1 (36 / 0 / 0) if Wife_education = 4 and wife_age 3 then 2 (0 / 14 / 0) if Wife_education = 1 and Husband_occupation = 2 then 1 (17 / 0 / 1) if Wife_education = 4 and wife_age > 33 and Num_children_born > 2 and Husband_occupation = 1 and Num_children_born <= 3 then 2 (1 / 10 / 2) Step7 Build Model(con’t)

24. if Num_children_born > 2 and wife_age 28 then 3 (1 / 0 / 13) if wife_age 4 and Media_exposure = 0 then 3 (1 / 2 / 12) if Husband_education = 4 and wife_age 37 then 2 (0 / 5 / 0) else 1 (305 / 168 / 281) Step7 Build Model(con’t)

25. Weka-JRip (Wife_education = 4) and (Num_children_born >= 3) and (wife_age >= 35) => method_used=2 (178.0/76.0) (wife_age = 3) => method_used=3 (271.0/120.0) (wife_age = 1) and (wife_age method_used=3 (106.0/51.0) => method_used=1 (771.0/342.0) Step7 Build Model(con’t)

26. Step 8 Assess Model Decision Tree

27. Step 8 Assess Model(con’t) Ripper Rule

28. Step 8 Assess Model(con’t) JRip Rule

29. Conclusion Result The problems we should improve  more data  ignore some attributes  details of the attribute are not so clear  period and environment have changed

30. Thanks for you listening…