Data Scientist, CHOICE


Full-timeEstimated: $140,000 - $190,000 a year
The Visiting Nurse Service of New York (VNSNY) is the nation’s largest not-for-profit home- and community-based health care organization, serving the five boroughs of New York City, and Nassau, Suffolk, and Westchester Counties. For 125 years, VNSNY has been committed to meeting the health care needs of New Yorkers with compassionate, high-quality home health care. We offer a wide range of services, programs, and health plans to meet the diverse needs of our patients, members, and clients from before birth to the end of life.

Each day, more than 13,000 VNSNY employees — including nurses, rehabilitation therapists, social workers, other allied professionals, and paraprofessionals — deliver compassionate care, unparalleled medical expertise, and 24/7 solutions and resources to more than 48,000 patients and members, helping them to live the best lives possible in their homes and communities.


About Our Team:
The Data Science Team provides advanced analytical support across VNSNY’s family of corporations. We leverage big data in a fast paced environment to support strategic decisions for the agency. Meaningful, appropriate use of data is central to the success of our organization. We are looking for an ambitious data scientist to join our expanding team.

About the Role:
The Data Scientist will join a core group of analysts who play an important role in generating strategic insights across the VNSNY organization within four functional areas:

Clinical analytics - “Who is going to get sick? What can we do to prevent or mitigate these health events? When is the best time to implement these actions?” This functional area examines the drivers of clinical outcomes; analyzes opportunities for managing risk-based populations; evaluates programs and interventions that aim to improve patient outcomes.
Quality analytics – “How is quality of care measured and how is it related to patient outcomes? Where are opportunities to improve the quality of care to our patients and members?” Analysts in this functional area serve as subject matter experts on healthcare quality measurement and risk adjustment; use predictive modeling to identify patient populations in need of clinical interventions; identify opportunities for improvement in clinical processes that can lead to improved quality of care.
Operational analytics – “How can we optimize our business operations in order to be more efficient? How do we deliver our services in order to improve the coordination of care for our patients and members?” This functional area focuses on efficiency and optimization of business practices in order to improve patient care; uses techniques including time series forecasting and geospatial analysis to address business problems such as staffing and scheduling; analyzes opportunities for business growth within the organization and predicts and forecasts expenses.
Policy analytics – “What is the impact of health care policy on our patient population? On our most vulnerable patients and members? How will changes in reimbursement policy affect the way we deliver patient care? What partnerships can we develop in order to ensure that our patients and members continue receiving optimal care?” Analysts in this functional area serve as subject matter experts on healthcare policy; analyze areas for meaningful value investments that focus on improving health outcomes while saving money; use predictive modeling to identify high cost and high need patient populations who may be impacted most by changes in health policy.

You Are:
Looking for an opportunity to leverage your training in data science and work alongside clinical, operational, and business stakeholders by developing and testing hypotheses to solve a wide variety of business challenges
Savvy in applying statistical modeling, data science, and experimental designs to complex problems and seek to engage in new challenges
Driven by curiosity and a passion to learn, you thrive in situations where you can bring clarity to ambiguous and multi-faceted problems
A logical thinker and can learn new programming languages, computing applications or data sources with limited support
Have a desire to use your analytical skills to make measurable impacts on the lives of patients

Master’s degree in statistics, biostatistics, mathematics, econometrics, epidemiology, computer science, or other statistics related degree
Professional experience: 2+ years
Experience performing complex data analysis and interpretation, preferably in a post-acute, long-term, or managed care health care setting
Programming experience with at least one statistical package (e.g., R, Python, Julia, MATLAB, SAS, Stata) with demonstrated ability to learn and wield multiple analytical tools
Knowledge of relational databases and programming experience in SQL or PLSQL
Ability to effectively communicate results of complex data analysis to non-statistical audiences through user-friendly data visualizations and reports
Ability to translate business needs into relevant data-driven deliverables and analyses
Demonstrated experience executing analyses in a timely, rigorous and reproducible manner
Ability to manage multiple projects independently, sometimes on tight deadlines
Excellent oral, written, and interpersonal communication skills and ability to work collaboratively across different teams
Demonstrated attention to detail; when you find data that looks wrong, you are emotionally compelled to figure out why

Nice to Have:
Experience with medical claims, electronic medical records, and health assessment data (e.g. OASIS, UAS-NY)
Knowledge of Medicare and Medicaid payment policy and alternative payment models (e.g. HHGM, Value Based Payment, dual-risk models, Hospice Final Rule)
Knowledge of risk adjustment strategies and application of risk adjustment to quality measurement programs such as CMS Home Health Quality Measures, CMS Home Health Value-Based Purchasing Model, CMS Hospice Quality Reporting Program, New York State MLTC Quality Incentive, HEDIS
Understanding of supervised and unsupervised data mining and predictive modeling techniques
Experience with operational analytics and applying operational research techniques to support strategic and operational decisions
Experience in quasi-experimental methods such as propensity score matching or instrumental variable analysis
Other programming experience (e.g., Java, C++)