Research Scientist 2

Humana•Louisville, KY

1d•$78,400 - $107,800•Hybrid

About The Position

Humana’s Healthcare Quality & Reporting Improvement (HQRI) department is seeking a Research Scientist 2 to join a high-performing team advancing predictive modeling and analytics in support of its Medicare and Medicaid business. The HQRI team delivers insights that support the effectiveness of risk adjustment initiatives. The Research Scientist 2 participates in research study design, analysis, and interpretation of results, with particular emphasis on statistical and analytical plan development; data acquisition, preparation, and management; and statistical analysis and interpretation of findings. Assignments are varied and frequently require interpretation and independent determination of appropriate courses of action. In partnership with a senior research scientist, this role applies advanced statistical methods to evaluate the impact of risk adjustment programs and pilot projects. Findings inform business decisions and operational strategies. The role also collaborates with colleagues in data science and actuarial analytics, contributing expertise in statistical analysis while learning from teammates. This is a hybrid position requiring work in the Louisville, Kentucky office two days per week. Candidates must live within reasonable commuting distance or be willing to relocate to Louisville. The position is not eligible for work visa sponsorship.

Requirements

Bachelor’s degree in Computer Science, Data Science, Mathematics, or a related quantitative field.
Two years of experience applying statistical modeling, predictive analytics, machine learning, or quantitative research methods in a healthcare, insurance, consulting, or data science environment.
Strong programming skills in Python and SQL.
Hands-on experience developing analytical and modeling solutions in Databricks, PySpark, or similar distributed data processing environments.
Experience building, calibrating, validating, and analyzing predictive models, including model performance evaluation, calibration techniques, and interpretation of modeling results.
Experience performing exploratory data analysis, feature engineering, and model performance assessment using large and complex datasets.
Ability to translate analytical findings into actionable business insights and communicate results effectively to technical and non-technical stakeholders.
Strong problem-solving, critical-thinking, and collaboration skills, with the ability to work effectively in a cross-functional environment.
Must reside within reasonable commuting distance of the Louisville, Kentucky office or be willing to relocate; the role requires working in the office two days per week.

Nice To Haves

Master’s degree or PhD in Computer Science, Data Science, Statistics, Mathematics, or a related quantitative discipline.
Experience with healthcare analytics, including Medicare, Medicaid, risk adjustment, HCC modeling, Stars/HEDIS, provider analytics, or population health programs.
Experience developing, maintaining, or optimizing machine learning models in cloud-based analytics platforms such as Databricks.
Strong understanding of model calibration methodologies, including Platt Scaling, Isotonic Regression, and score normalization approaches.
Experience working with large-scale healthcare datasets, claims data, medical records, encounter data, or clinical data sources.
Familiarity with machine learning libraries such as scikit-learn, XGBoost, LightGBM, TensorFlow, or PyTorch.

Responsibilities

Participate in research study design, analysis, and interpretation of results.
Develop statistical and analytical plans.
Acquire, prepare, and manage data.
Perform statistical analyses and interpret findings.
Partner with a senior research scientist to apply advanced statistical methods to evaluate risk adjustment programs and pilot projects.
Build, calibrate, validate, and analyze predictive models, including evaluating performance and interpreting results.
Perform exploratory data analysis, feature engineering, and model performance assessment using large and complex datasets.
Translate analytical findings into actionable business insights and communicate results to technical and non-technical stakeholders.
Collaborate with colleagues specializing in data science and actuarial analytics.