Work Comp Predictive Models
There are so many articles on Work Comp predictive models out in the blogosphere. Many taut their ability to see into the future. I am not a big fan of predictive models as I have yet to see and am still waiting on one that is consistent in nature.

One of the larger carriers in the nation had a predictive algorithm for setting claim reserves. The reserves were off approximately 60% when I attempted a loss run review. The carrier has since quit using the algorithm.
Some types of insurance can be held up to a predictive model such as automobile or property loss. Workers comp predictive models attempt to predict how the human body heals as part of its forecasting.
The healing of the human body is such a random event. In that same light, I came across an article that seemed to say gut feelings is actually a learned predictive algorithm learned since birth. The article published in Inc magazine was an interesting take on how we all carry around a built in algorithm.
A great passage from the article – “the more we experience- the more accurate our gut instincts become.”
The great Cris Carter- (former Vikings receiver) said the players that practice more seem to have more luck.

If you follow the link to the article, there is a great example of how Gary Player the golfer used gut instinct as part of his luck.
Workers comp adjusters develop this “gut instinct” after 5 – 7 years of experience on which claims to question; how much medical reserves to place on a file; which claims need another medical opinion; etc.
As I have often mentioned, if I happen to come across any Work Comp predictive models or algorithms that work, I will laud it heavily- but then again I am still waiting.
I will publish a similar article on how this all fits in with a business owner next time.
©J&L Risk Management Inc Copyright Notice
4 Responses
Your wait should be over. They work. I’ve seen the data.
By working, it does not mean on every single account, but on a portfolio of accounts. If you are expecting the model to be perfect (“consistent”) on every account, then you will never laud the models. However, the results are amazing on a book of business.
Well, if we all had the same brains, the same education and the same experiences, then our cumulative “gut feelings” mightbe the same as well. But that is simply not the case. In my experience, humans and claim professionals are not all the same. A claims professional may range from just out of orientation to those with 20 years of experience or those with 20 years of one years experience.
Our research and that of others has shown that there are certain bio-pyscho-social risk factors, that place injured workers at much greater risk of delayed recovery. Being able to quantify that risk at time of injury enables a brand new claim professional to know he or she has a potential difficult claim on thier hands as well as the seasoned veteran. It also provides a quantitative tool to support the use of additional resources such as case management or medical peer review to prevent the claim from running off the rails…..But the more important value is in the ability to better understand how these bio-pyscho-soclai risk factors play a much larger role in the occurance and severity of a claim than the physical risks (loss control focus) of a workplace.
Michael, Thanks for responding to the article. You have an interesting angle.
Frank, I do agree with you partially. Predictive models do work in certain circumstances, especially on the front end – not so much in claims data analysis. Liberty Mutual seems to be developing a model from their massive database. Thanks for responding to the article.