Tag Archives: predictive analytics

Capabilities of predictive analytics increase as technology advances

Today actuaries and insurers are able to apply predictive analytics in novel ways because of advanced technologies, larger data sets, and increased computing power. A recent Risk & Insurance article featuring Milliman’s Peggy Brinkman and Phil Borba explores four key areas where advances in predictive analytics are changing the way insurers conduct business: claims, driving safety, property risk, and competitive rating.

Validating machine-learning models

While machine-learning techniques can improve business processes, predict future outcomes, and save money, they also increase modeling risk because of their complex and opaque features. In this article, Milliman’s Jonathan Glowacki and Martin Reichhoff discuss how model validation techniques can mitigate the potential pitfalls of machine-learning algorithms.

Here is an excerpt:

An independent model validation carried out by knowledgeable professionals can mitigate the risks associated with new modeling techniques. In spite of the novelty of machine-learning techniques, there are several methods to safeguard against overfitting and other modeling flaws. The most important requirement for model validation is for the team performing the model validation to understand the algorithm. If the validator does not understand the theory and assumptions behind the model, then they are likely to not perform an effective model validation on the process. After demonstrating an understanding on the model theory, the following procedures are helpful in performing the validation.

Outcomes analysis refers to comparing modeled results to actual data. For advanced modeling techniques, outcomes analysis becomes a very simple yet useful approach to understanding model interactions and pitfalls. One way to understand model results is to simply plot the range of the independent variable against both the actual and predicted outcome along with the number of observations. This allows the user to visualize the univariate relationship within the model and understand if the model is overfitting to sparse data. To evaluate possible interactions, cross plots can also be created looking at results in two dimensions as opposed to a single dimension. Dimensionality beyond two dimensions becomes difficult to evaluate, but looking at simple interactions does provide an initial useful understanding of how the model behaves with independent variables….

…Cross-validation is a common strategy to help ensure that a model isn’t overfitting the sample data it’s being developed with. Cross-validation has been used to help ensure the integrity of other statistical methods in the past, and with the rising popularity of machine-learning techniques, it has become even more important. In cross-validation, a model is fitted using only a portion of the sample data. The model is then applied to the other portion of the data to test performance. Ideally, a model will perform equally well on both portions of the data. If it doesn’t, it’s likely that the model has been over fit.

Predictive analytics for the mortgage industry

How can predictive analytics help Government National Mortgage Association (GNMA/Ginnie Mae) issuers decide whether they want to buy out a nonperforming loan or not? In their article “Enhanced vision,” Milliman’s Jonathan Glowacki and Makho Mashoba provide perspective on an algorithm used to analyze loans that are likely to bounce back in order to reissue them as a mortgage-backed security.

Here is an excerpt:

The XGBoost model, like similar algorithms, is easy to implement. Once the mechanics of the technique are understood, and the parameters are tuned correctly, the model can be turned on a data set to produce accompanying predictions. The model can be updated continuously each month based on new data feeds. Pointing an XGBoost program toward a new data set and running it again is virtually all that is needed to refresh the results. It is also possible to retune the parameters for the update to further enhance the effects.

A use case of this type of model would be to pursue early buyouts for mortgages that have a high probability of re-performing and potentially not pursue early buyouts for mortgages that have a low probability of re-performing, as long as this policy is consistent with GNMA servicing guidelines.

This same technique can be used on a variety of data for alternative purposes. Predictive analytics can capture predictive power from internal data, whether that involves established and go-to data sets or whether that involves bringing together data from across an organization to make predictions. Predictive analytics can also help a firm leverage industry data and other outside sources to forecast trends or improve decisions. This case is a concrete example of how using the tool should result in higher return on investment on GNMA early buyouts.

Considering the growing amounts of data available, the mortgage industry should pay attention to predictive analytics tools. Investing in the technology has proven to generate significant returns. GNMA issuers is just one group to which predictive analytics can be applied. Predictive analytics can be applied to many other techniques and tools to increase efficiencies within the mortgage industry. The future depends on it.

BETA Healthcare Group teams with Milliman Datalytics-Defense to develop data-driven defense strategies

Milliman today announced that BETA Healthcare Group has chosen Milliman Datalytics-Defense® as its platform for processing its defense cost invoices. Datalytics employs powerful data mining algorithms to help insurers detect patterns in attorney billing practices, delivering better understanding of both costs and defense strategies.

“It’s BETA’s goal to find innovative strategies to mitigate risk and reduce costs when it comes to managing our business,” says Tom Wander, CEO of BETA Healthcare Group. “Partnering with Milliman Datalytics-Defense helps us make more well-informed, data-driven decisions in our defense strategies, something we believe is essential to remain a leader in the industry.”

Milliman Datalytics-Defense provides real-time, actionable intelligence through responsive reporting dashboards that are built upon a robust data warehouse. The web-based tool is available on a subscription basis and can perform peer comparisons, allowing insurers to credibly benchmark their defense costs. The tool’s predictive analytic engine helps insurers develop best practices of claims defense.

“BETA has a reputation as a forward-thinking organization that knows success in the industry today must include cutting-edge tools such as Datalytics to manage claims effectively and efficiently,” says Chad C. Karls, Milliman principal and consulting actuary. “We look forward to working with BETA to identify claims handling strategies that will benefit not only BETA, but ultimately their members/insureds.”

To learn more about Milliman Datalytics-Defense, click here.

Constellation’s choice of Milliman Datalytics-Defense puts them at the forefront of claims defense management

Milliman today announced that Constellation has chosen Milliman Datalytics-Defense® as its platform for processing its defense cost invoices. Datalytics employs powerful data mining algorithms to help insurers detect patterns in attorney billing practices, delivering better understanding of both costs and defense strategies.

“With Milliman Datalytics-Defense we are excited about being able to extract additional intelligence from our defense cost data in order to assist us in making informed, data-driven decisions in our defense strategies moving forward,” says Steve Lacke, Constellation Chief Operating Officer. “While the MPL industry has experienced an unprecedented drop in frequency since the early 2000s, the cost of defending claims has not gone down commensurately. When we went to market to find a new tool to assist us in managing that cost curve, Datalytics was clearly different, and showed the greatest promise for us.”

Milliman Datalytics-Defense provides real-time, actionable intelligence through responsive reporting dashboards that are built upon a robust data warehouse. The web-based tool is available on a subscription basis and can perform peer comparisons, allowing insurers to credibly benchmark their defense costs. The tool’s predictive analytic engine helps insurers develop best practices of claims defense.

“We look forward to working with Constellation to identify cost-effective claims handling strategies by unlocking the information that is hidden in their defense costs invoices and turning it into actionable data,” says Chad C. Karls, Milliman principal and consulting actuary. “Constellation has a reputation of being forward-thinking and we believe that this move puts them at the forefront of ALAE management—something the entire MPL industry has struggled with for over a decade now.”

To learn more about Milliman Datalytics-Defense, click here.

NORCAL Mutual chooses Milliman Datalytics-Defense® to help improve claims handling with data-driven decision support

Milliman today announced that NORCAL Mutual has chosen Milliman Datalytics-Defense® as its platform for managing its defense costs. Datalytics employs powerful data mining algorithms to help insurers evaluate costs associated with defending claims in order to identify opportunities to improve results.

“We chose Milliman Datalytics-Defense because of its ability to provide an efficient approach to managing defense costs while increasing our ability to turn data into information…,” says Timothy J. Friers, NORCAL Mutual Senior Vice President and Chief Operating Officer. “The tool allows us to gain greater insight into our results and improve our claims defense strategies for the benefit of our insureds.”

Milliman Datalytics-Defense provides real-time, actionable intelligence through responsive reporting dashboards that are built upon a robust data warehouse. The web-based tool is available on a subscription basis and can perform peer comparisons, allowing insurers to credibly benchmark their defense costs. The tool’s predictive analytic engine helps insurers develop best practices of claims defense.

“Milliman Datalytics-Defense uses advanced text mining to unlock information that was previously hidden in defense costs invoices,” says Chad C. Karls, Milliman Principal and Consulting Actuary.

To learn more about Milliman Datalytics-Defense, click here.