Data Scientist

Huron helps its clients drive growth, enhance performance and sustain leadership in the markets they serve. We help healthcare organizations build innovation capabilities and accelerate key growth initiatives, enabling organizations to own the future, instead of being disrupted by it. Together, we empower clients to create sustainable growth, optimize internal processes and deliver better consumer outcomes.

Health systems, hospitals and medical clinics are under immense pressure to improve clinical outcomes and reduce the cost of providing patient care. Investing in new partnerships, clinical services and technology is not enough to create meaningful and substantive change. To succeed long-term, healthcare organizations must empower leaders, clinicians, employees, affiliates and communities to build cultures that foster innovation to achieve the best outcomes for patients.

Joining the Huron team means you’ll help our clients evolve and adapt to the rapidly changing healthcare environment and optimize existing business operations, improve clinical outcomes, create a more consumer-centric healthcare experience, and drive physician, patient and employee engagement across the enterprise.

Join our team as the expert you are now and create your future.

A highly motivated and detail-oriented Associate - Data Scientist with a strong foundation in statistics, machine learning, classification, regression, clustering, recommendation, anomaly detection, Natural Language Processing (NLP) and healthcare data analytics. This role requires hands-on experience in building and deploying predictive models, conducting clustering and segmentation analysis, applying Market Basket Analysis (MBA) for root cause pattern discovery, and utilizing supervised and unsupervised ML techniques to uncover insights from complex datasets. Coordinate with the stakeholders to develop data-driven solutions that address challenges in denials, collections, write-offs, and payment forecasting.

Job Title: Data Scientist
Practice: Healthcare
Level: Associate
Location: Bangalore

Key Responsibilities:

• Analyze large-scale healthcare claims and transaction data (charges, payments, denials, write-offs, etc.)
• Develop and implement predictive models, such as XGBoost, Random Forest, or Logistic Regression, for denial prediction, transaction classification, and payment forecasting
• Apply unsupervised learning techniques (e.g., clustering, MBA) to detect denial root causes, payer patterns, and operational inefficiencies.
• Identify trends and anomalies to support root cause analysis in denials and underpayments
• Build and validate machine learning models likw classification, forecasting, clustering for Denial prediction and pattern recognition, Cash collection forecasting and Write-off root cause analysis
• Use tools such as Python (scikit-learn, XGBoost, pandas), SQL, and AWS services like SageMaker, Athena
• Translate business problems into machine learning problems and deliver solutions with clear, measurable outcomes.
• Collaborate with business stakeholders to define use cases and translate them into analytical models and interactive insights
• Work with large datasets from AWS Redshift, S3, Oracle, SageMaker, Excel, and other sources to preprocess and prepare training datasets
• Provide statistical analysis and model validation to ensure accuracy and reliability on unseen RCM data
• Automate and replace manual Excel-based reports with AI-powered analytics and decision support tools
• Collaborate with data visualization teams to integrate model outputs into business-friendly dashboards using AWS QuickSight or Power BI
• Assist in integrating models into production environments and monitoring performance
• Work closely with domain experts, operations leaders, and client teams to translate business questions into analytical solutions
• Participate in brainstorming sessions for new use cases and innovations




Required Qualifications & Skills:
• 5+ Yrs of experience in analytics and Data science
• Proficient in Python and SQL for data transformation and model building
• Hands-on experience with supervised and unsupervised ML techniques, including clustering, classification, and association rule mining
• Exposure to statistics, hypothesis testing, and model performance evaluation techniques (e.g., ROC-AUC, precision/recall, F1)
• Experience with AWS tools such as SageMaker, Redshift, Athena, S3; familiarity with Snowflake is a plus
• Preferred knowledge on Revenue Cycle Management
• Exposure to Python, SQL and data querying for extracting insights and Excel formulae
• Good communication skills and ability to work with business teams.
• Eagerness to learn cloud-based data tools (AWS, S3, Redshift, Snowflake, etc.)

Position Level

Associate

Country

India