Page 364 - Contributed Paper Session (CPS) - Volume 6
P. 364
CPS1966 Jessa L. S. C. et al.
for clients looking for protection. They can be offered to the dependents of a
breadwinner or to the owner himself especially if he is earning much and has
a lot to lose. Other Traditional is also an option for protection push but it caters
to the extreme segments in terms of income earnings. Hence, Unit-linked
product as a protection solution can be used to target the middle class.
These results can be supplemented by qualitative studies that can validate
the targeting strategy. For example, actual clients can be asked through a
survey if they will be interested to purchase a Unit-linked product. Similarly, it
can be checked if indeed the reason why higher life insurance cover is
purchased is because of protection and not for higher premium which can
generate higher investment. Either way, this quantitative study can be used as
a basis and a starting point for a qualitative study.
References
1. Breiman, L. (October 2001). Random Forest. Machine Learning, 45.
Retrieved from:
https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf
2. Breiman, L. (1996). Bagging Predictors. Machine Learning, 24. Retrieved
from: https://link.springer.com/article/10.1023/A:1018054314350
3. Fawagreh, K., et al. (August 2014). Random forests: from early
developments to recent advancements. Systems Science & Control
Engineering: An Open Access Journal, 2. Retrieved from: https:
https://www.tandfonline.com/doi/abs/10.1080/21642583.2014.956265
4. Gass, K., et al. (2014). Classification and regression trees for
epidemiologic research: an air pollution example. Environment Health
Journal, 13. Retrieved from: http://www.ehjournal.net/content/13/1/17
5. Gromping, U. (November 2009). Variable Importance Assessment in
Regression: Linear Regression versus Random Forest. American
Statistical Association, 63. Retrieved from:
https://www.tandfonline.com/doi/abs/10.1198/tast.2009.08199
6. Hosmer, D., & Lemeshow, S. (2000). Applied Logistic Regression (2 ed.).
nd
Hoboken, New Jersey: John Wiley & Sons, Inc.
7. Izenman, A. (2008). Modern Multivariate Statistical Techniques. New
York: Springer Science+Business Media
8. Jay, M. (December 2017). Goodness of Fit Tests for Logistic Regression
Models. Retrieved from: https://cran.r-
project.org/web/packages/generalhoslem/generalhoslem.pdf
9. Loh, W. (January 2011). Classification and regression trees. WIREs Data
Mining and Knowledge Discovery, 1. Retrieved from:
https://www.stat.wisc.edu/~loh/treeprogs/guide/wires11.pdf
353 | I S I W S C 2 0 1 9