Chao: Health Insurance Marketplace is Still Incomplete

Henry Chao the deputy chief information officer at the Centers for Medicare and Medicaid Services said that the federal health insurance marketplace is not yet complete. He said that they are still building the �back office systems." 

�we still have to build the financial management aspects of the system, which includes our accounting system and payment system and reconciliation system,� he said. "This part is still being developed and will be tested."

He admitted Tuesday that up to 40 percent of IT systems supporting the exchange still need to be built.

The Obama government completed the online system which allowed consumers to apply for insurance, compare health plans and enroll however, many parts of the system were still being repaired and were not performing as well as they had hoped.

�It�s not that it�s not working,� Chao told lawmakers at an Energy and Commerce Oversight and Investigations subcommittee hearing. �It�s still being developed and tested.�

Financial management tools are not yet done, he said, particularly the process that will deliver payments to insurers.

Predicting claims with a Bayesian network

Here is a little Bayesian Network to predict the claims for two different types of drivers over the next year, see also example 16.15 in [1].

Let's assume there are good and bad drivers. The probabilities that a good driver will have 0, 1 or 2 claims in any given year are set to 70%, 20% and 10%, while for bad drivers the probabilities are 50%, 30% and 20% respectively.

Further I assume that 75% of all drivers are good drivers and only 25% would be classified as bad drivers. Therefore the average number of claims per policyholder across the whole customer base would be:

0.75*(0*0.7 + 1*0.2 + 2*0.1) + 0.25*(0*0.5 + 1*0.3 + 2*0.2) = 0.475

Now a customer of two years asks for his renewal. Suppose he had no claims in the first year and one claim last year. How many claims should I predict for next year? Or in other words, how much credibility should I give him?

To answer the above question I present the data here as a Bayesian Network using the gRain package [2]. I start with the contingency probability tables for the driver type and the conditional probabilities for 0, 1 and 2 claims in year 1 and 2. As I assume independence between the years I set the same probabilities. I can now review my model as a mosaic plot (above) and as a graph (below) as well.

Next, I set the client's evidence (0 claims in year one and 1 claim in year two) and propagate these back through my network to estimate the probabilities that the customer is either a good (73.68%) or a bad (26.32%) driver. Knowing that a good driver has on overage 0.4 claims a year and a bad driver 0.7 claims I predict the number of claims for my customer with the given claims history as 0.4789.


Alternatively I could have added a third node for year 3 and queried the network for the probabilities of 0, 1 or 2 claims given that the customer had zero claims in year 1 and one claim in year 2. The sum product of the number of claims and probabilities gives me again an expected claims number of 0.4789.

References

[1] Klugman, S. A., Panjer, H. H. & Willmot, G. E. (2004), Loss Models: From Data to Decisions, Wiley Series in Proability and Statistics.

[2] S�ren H�jsgaard (2012). Graphical Independence Networks with the gRain Package for R. Journal of Statistical Software, 46(10), 1-26. URL http://www.jstatsoft.org/v46/i10/

Session Info

R version 3.0.2 (2013-09-25)
Platform: x86_64-apple-darwin10.8.0 (64-bit)

locale:
[1] en_GB.UTF-8/en_GB.UTF-8/en_GB.UTF-8/C/en_GB.UTF-8/en_GB.UTF-8

attached base packages:
[1] grid      stats     graphics  grDevices utils     datasets  methods  
[8] base     

other attached packages:
[1] Rgraphviz_2.6.0 gRain_1.2-2     gRbase_1.6-12   graph_1.40.0   

loaded via a namespace (and not attached):
[1] BiocGenerics_0.8.0 igraph_0.6.6       lattice_0.20-24    Matrix_1.1-0      
[5] parallel_3.0.2     RBGL_1.38.0        stats4_3.0.2       tools_3.0.2