Senior Data Scientist

Bellese is a mission-driven Digital Services Company committed to pioneering innovative technology solutions in civic healthcare. Our dedication lies in making a meaningful impact on public health outcomes. Driven by service design, we strive to know the “Why” to understand the healthcare journey for patients, caregivers, providers, payers, and policymakers. Our goal is to design and build solutions that reduce confusion, provide clarity, support decision making, and streamline the process so that we and our partners can focus on providing better health outcomes by improving patient care and reducing costs and burden. The Team you will be joining: HQR Our team is charged with maintaining and improving the software at the Centers for Medicare and Medicaid Services (CMS) that supports the Hospital Quality Reporting program. Thousands of hospitals across the country depend on these systems to submit quality measure data that reflects the care beneficiaries receive in their facility. Our teams will continuously strive to modernize these systems, while improving them in ways that reduce provider burden and minimize costs to CMS. We do this through HCD and Service design practices, product thinking, and skilled engineering. At Bellese, we’re relentlessly focused on enabling and empowering providers to focus on improving the quality and safety of patient care. What you will be doing as a Senior Data Scientist: Work collaboratively with Human Centered Design lead to take input from the below forums, analyze the data, visualize the data, and form insights and predictions supporting the Centers for Medicare & Medicaid Services (CMS) initiatives to increase price transparency for healthcare consumers through price shopping alternatives: Healthcare industry research, Academic research, Public data sets, Medicare claims data, Web analytics data, Ideation sessions with the client, Qualitative & quantitative user research Support the product design process with data in a way that reflects and responds to the functional, social, and emotional behavior of users Build predictive models, data visualizations, and tools for analysis Build AI tools that automate processes, recommendation engines, and automated lead scoring systems Provide insights through the combination of qualitative design research and exploratory data analysis Research and analyze data sources for patterns and clusters to help further the analysis process developing features for the CMS Procedure Price Lookup (PPL) tool Create data visualizations that tell stories to help stakeholders and end users understand a problem space or lead to an insight Ability to solve problems while considering timeliness, effectiveness, and practicality in addressing product needs. Ability to apply critical thinking skills to conduct an objective analysis of facts on a given topic or problem before formulating opinions or rendering judgments Programming skills in R, Python and/or other programming languages used for data science purposes Ability to collaborate closely with business and technical leaders. Ability to work with machine learning frameworks, such as TensorflowWork in an agile environment, delivering incremental product functionality in short iterations Selecting features, building and optimizing classifiers using machine learning techniques Data mining using state-of-the-art methods Enhancing data collection procedures to include information that is relevant for building analytic systems Processing, cleansing, and verifying the integrity of data used for analysis Performing ad-hoc analysis and presenting results in a clear manner Creating an automated anomaly detection system and constant tracking of its performance Participate in product discussions with the product owner, users, and the development team to understand and refine acceptance criteria and estimate user stories Required Qualifications & Experience Experience with Python, PySpark, R Experience with unsupervised and supervised machine learning techniques and algorithms, such as k-NN, Naive Bayes, SVM, Decision Forests, etc. Experience with common data science toolkits, such as R, Weka, NumPy, MatLab, etc. Experience with data visualization tools Experience applying statistical methods and concepts, such as distributions, statistical testing, regression, etc. Experience with Sparklyr