--- title: Testing Alternative Regression Frameworks for Predictive Modeling of Health Care Costs description: January 2016 | I. Duncan, M. Loginov, & M. Ludkovski --- Publication # Testing Alternative Regression Frameworks for Predictive Modeling of Health Care Costs [ Arbital Health ](https://arbitalhealth.com/blog/author/arbital-health) Jan 8, 2016 [mailto:?subject=Check%20out%20https://arbitalhealth.com/blog/testing-alternative-regression-frameworks-for-predictive-modeling-of-health-care-costs&utm_medium=social&utm_source=email%20&body=Check%20out%20https://arbitalhealth.com/blog/testing-alternative-regression-frameworks-for-predictive-modeling-of-health-care-costs&utm_medium=social&utm_source=email](mailto:?subject=Check%20out%20https://arbitalhealth.com/blog/testing-alternative-regression-frameworks-for-predictive-modeling-of-health-care-costs&utm_medium=social&utm_source=email%20&body=Check%20out%20https://arbitalhealth.com/blog/testing-alternative-regression-frameworks-for-predictive-modeling-of-health-care-costs&utm_medium=social&utm_source=email) [Publication](https://arbitalhealth.com/blog/tag/publication) Published: January 8, 2016 Publisher: North American Actuarial Journal By: I. Duncan, M. Loginov, & M. Ludkovski   Abstract Predictive models of health care costs have become mainstream in much health care actuarial work. The Affordable Care Act requires the use of predictive modeling-based risk-adjuster models to transfer revenue between different health exchange participants. Although the predictive accuracy of these models has been investigated in a number of studies, the accuracy and use of models for applications other than risk adjustment have not been the subject of much investigation. We investigate predictive modeling of future health care costs using several statistical techniques. Our analysis was performed based on a dataset of 30,000 insureds containing claims information from two contiguous years. The dataset contains more than 100 covariates for each insured, including detailed breakdown of past costs and causes encoded via coexisting condition flags. We discuss statistical models for the relationship between next-year costs and medical and cost information to predict the mean and quantiles of future cost, ranking risks and identifying most predictive covariates. A comparison of multiple models is presented, including (in addition to the traditional linear regression model underlying risk adjusters) Lasso GLM, multivariate adaptive regression splines, random forests, decision trees, and boosted trees. A detailed performance analysis shows that the traditional regression approach does not perform well and that more accurate models are possible.   [ Read Full Publication ](https://www.tandfonline.com/doi/abs/10.1080/10920277.2015.1110491)   ### View More News & Insights from the Arbital Health Team: Publication ### [A prediction model for targeting low-cost, high-risk members of managed care organizations](https://arbitalhealth.com/blog/a-prediction-model-for-targeting-low-cost-high-risk-members-of-managed-care-organizations) Arbital Health May 9, 2003 Publication ### [Mining Health Claims Data for Assessing Patient Risk](https://arbitalhealth.com/blog/mining-health-claims-data-for-assessing-patient-risk) Arbital Health Jan 1, 2012 Publication ### [Predicting High Need End-of-Life in Medicare Patients through Machine Learning](https://arbitalhealth.com/blog/predicting-high-need-end-of-life-in-medicare-patients-through-machine-learning) Arbital Health Jul 21, 2023 ### Sign-Up for Arbital Health Email Updates Unlock a wealth of valuable insights and stay ahead of the curve with Arbital Health's exclusive email updates. Join our community of forward-thinkers and industry leaders to receive the latest news, upcoming webinar alerts, and crucial developments in VBC strategies straight to your inbox. Don't miss out on the opportunity to stay informed, connected, and empowered in the ever-evolving landscape of healthcare. | SOLUTIONS | WHO WE SERVE | WHO WE ARE | RESOURCES | | --- | --- | --- | --- | | [Arbital Platform](https://arbitalhealth.com/adjudication-platform) [Actuarial Services](https://arbitalhealth.com/actuarial-services) [Arbital AI](https://arbitalhealth.com/merlin-ai) [Arbital ATLAS](https://arbitalhealth.com/atlas) [Arbital Flex](https://arbitalhealth.com/flex) | [Providers](https://arbitalhealth.com/who-we-serve) [Payers](https://arbitalhealth.com/who-we-serve#Payers) [Value-Based Care Enablers](https://arbitalhealth.com/who-we-serve#RiskBearingEntities) [Employers](https://arbitalhealth.com/who-we-serve#Employers) | [About Us](https://arbitalhealth.com/about-us) [Our Team](https://arbitalhealth.com/our-team) [Careers](https://arbitalhealth.com/careers) | [All Content](https://arbitalhealth.com/blog) [Blog](https://arbitalhealth.com/blog/tag/blog#blog) [Press Releases](https://arbitalhealth.com/blog/tag/press-release#blog) [Talks](https://arbitalhealth.com/blog/tag/talks#blog) [Events](https://arbitalhealth.com/blog/tag/events#blog) **[Privacy Policy](https://arbitalhealth.com/privacy-policy)** |   STAY IN TOUCH Join a network of innovators shaping the future of healthcare. Receive timely updates, exclusive event invitations, and expert insights on value-based care strategies. ![SUBSCRIBE TO OUR NEWSLETTER](https://no-cache.hubspot.com/cta/default/44728686/interactive-193352706174.png) By submitting, I give Arbital Health permission to store and process your personal information so we can provide you with the content you’ve requested. ![Arbital_Logo_Full_Color_KO_rgb_022124](https://arbitalhealth.com/hubfs/Arbital_Logo_Full_Color_KO_rgb_022124.png) 98 Battery Street, Suite 400, San Francisco, CA    94111 (415) 226-9393 © Arbital Health. All Rights Reserved 2025. ![](https://px.ads.linkedin.com/collect/?pid=6309914&fmt=gif) ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Person", "name" : "Arbital Health", "url" : "https://arbitalhealth.com/blog/author/arbital-health" }, "dateModified" : "2025-02-06T18:11:01.327Z", "datePublished" : "2016-01-08T08:00:00.000Z", "headline" : "Testing Alternative Regression Frameworks for Predictive Modeling of Health Care Costs", "mainEntityOfPage" : { "@id" : "https://arbitalhealth.com/blog/testing-alternative-regression-frameworks-for-predictive-modeling-of-health-care-costs", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://arbitalhealth.com/hubfs/Branding%20Assets/Arbital_Logo_020524-1.png" }, "name" : "Arbital Health" } } ```