HIDDEN MARKOV MODEL APPROACH TO DISABILITY INCEPTION PROBABILITY WITH EXPECTATION MAXIMIZATION ALGORITHM
Insurance companies are institutions that bear the risk of their customers. In order for insurance companies can continue to run, it is necessary to know the risks faced in the future. Disability is an example of risk that can be borne by insurance companies. In this final project, a disability ince...
Saved in:
Main Author: | |
---|---|
Format: | Final Project |
Language: | Indonesia |
Online Access: | https://digilib.itb.ac.id/gdl/view/64992 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Institut Teknologi Bandung |
Language: | Indonesia |
id |
id-itb.:64992 |
---|---|
spelling |
id-itb.:649922022-06-20T07:38:04ZHIDDEN MARKOV MODEL APPROACH TO DISABILITY INCEPTION PROBABILITY WITH EXPECTATION MAXIMIZATION ALGORITHM Cannarivo Buntarco, Reuven Indonesia Final Project disability insurance, Markov chain, hidden Markov model, expectation maximization algorithm INSTITUT TEKNOLOGI BANDUNG https://digilib.itb.ac.id/gdl/view/64992 Insurance companies are institutions that bear the risk of their customers. In order for insurance companies can continue to run, it is necessary to know the risks faced in the future. Disability is an example of risk that can be borne by insurance companies. In this final project, a disability inception probability model is built using the hidden Markov model where the probability of disability inception is influenced by the age group which the information has been obtained and the unobserved time trend. This hidden Markov model is estimated with the expectation maximization algorithm and compared with the time series model. As an initial guess, the parameters will be estimated using logistic regression. The mean squared error is used to select the best model and the efficiency is taken into account in obtaining model parameters. text |
institution |
Institut Teknologi Bandung |
building |
Institut Teknologi Bandung Library |
continent |
Asia |
country |
Indonesia Indonesia |
content_provider |
Institut Teknologi Bandung |
collection |
Digital ITB |
language |
Indonesia |
description |
Insurance companies are institutions that bear the risk of their customers. In order for insurance companies can continue to run, it is necessary to know the risks faced in the future. Disability is an example of risk that can be borne by insurance companies. In this final project, a disability inception probability model is built using the hidden Markov model where the probability of disability inception is influenced by the age group which the information has been obtained and the unobserved time trend. This hidden Markov model is estimated with the expectation maximization algorithm and compared with the time series model. As an initial guess, the parameters will be estimated using logistic regression. The mean squared error is used to select the best model and the efficiency is taken into account in obtaining model parameters. |
format |
Final Project |
author |
Cannarivo Buntarco, Reuven |
spellingShingle |
Cannarivo Buntarco, Reuven HIDDEN MARKOV MODEL APPROACH TO DISABILITY INCEPTION PROBABILITY WITH EXPECTATION MAXIMIZATION ALGORITHM |
author_facet |
Cannarivo Buntarco, Reuven |
author_sort |
Cannarivo Buntarco, Reuven |
title |
HIDDEN MARKOV MODEL APPROACH TO DISABILITY INCEPTION PROBABILITY WITH EXPECTATION MAXIMIZATION ALGORITHM |
title_short |
HIDDEN MARKOV MODEL APPROACH TO DISABILITY INCEPTION PROBABILITY WITH EXPECTATION MAXIMIZATION ALGORITHM |
title_full |
HIDDEN MARKOV MODEL APPROACH TO DISABILITY INCEPTION PROBABILITY WITH EXPECTATION MAXIMIZATION ALGORITHM |
title_fullStr |
HIDDEN MARKOV MODEL APPROACH TO DISABILITY INCEPTION PROBABILITY WITH EXPECTATION MAXIMIZATION ALGORITHM |
title_full_unstemmed |
HIDDEN MARKOV MODEL APPROACH TO DISABILITY INCEPTION PROBABILITY WITH EXPECTATION MAXIMIZATION ALGORITHM |
title_sort |
hidden markov model approach to disability inception probability with expectation maximization algorithm |
url |
https://digilib.itb.ac.id/gdl/view/64992 |
_version_ |
1822932601997885440 |