Data Scientist

Job Description

– Assistant Manager Key Responsibilities Lead and own end-to-end data science and machine learning initiatives, from business problem identification and scoping through data preparation, modeling, validation, deployment, and monitoring. Develop predictive and prescriptive analytics solutions to support medical utilization management, including the detection of fraud, waste, abuse, and error (FWAE). Translate complex business and healthcare-related problems into data-driven analytical and machine learning solutions. Conduct exploratory data analysis (EDA) to identify trends, patterns, anomalies, relationships, and opportunities within healthcare and utilization data. Design, develop, test, and optimize machine learning models using appropriate algorithms and statistical techniques. Handle complex and highly imbalanced datasets, particularly rare-event problems such as FWAE and anomaly detection. Evaluate model performance using appropriate statistical and machine learning metrics, including Precision, Recall, F1-Score, ROC-AUC, RMSE, lift, and gain curves. Apply cost-sensitive evaluation and threshold optimization to assess the potential business value and deployment readiness of models. Perform data wrangling, cleansing, transformation, feature engineering, and validation to ensure data quality and model reliability. Develop analytical dashboards, visualizations, and reports to communicate insights and support management decision-making. Present analytical findings, model results, business implications, and recommendations to senior management and executive stakeholders. Translate technical and statistical findings into clear, actionable recommendations for Health Network Management, Utilization Management, and other business stakeholders. Identify opportunities to automate repetitive analytics and data science processes and implement scalable solutions. Collaborate with Data Analysts, Data Engineers, IT teams, healthcare teams, and business stakeholders to ensure successful implementation of analytics solutions. Establish and promote best practices in data science, model development, documentation, validation, and governance. Provide technical guidance and coaching to junior data scientists or analysts and contribute to the continuous improvement of the analytics team. Monitor deployed models and analytical solutions to ensure continued accuracy, relevance, and business effectiveness. Ensure that data science initiatives align with organizational objectives, healthcare business requirements, data privacy, and applicable policies and standards. Required Experience 2–4 years of professional experience in Data Science, Machine Learning, Advanced Analytics, or a related field, with at least 1 year of hands-on data science experience. Experience developing and implementing end-to-end machine learning models in a professional or production environment. Experience in predictive and/or prescriptive analytics, including problem formulation, feature engineering, model development, evaluation, and interpretation. Experience using Python and SQL for data analysis, data manipulation, and machine learning. Experience with supervised and unsupervised machine learning techniques. Experience developing solutions involving anomaly detection, fraud detection, risk scoring, or similar use cases is an advantage. Experience in healthcare, HMO, insurance, claims, utilization management, fraud analytics, or financial risk analytics is highly preferred. Experience in process automation or developing reusable analytics pipelines is an advantage. Experience mentoring or providing technical guidance to junior analysts or data science professionals is preferred for the Assistant Manager level. Must have at least one end-to-end data science project that was personally owned and implemented for actual business use, beyond academic or coursework projects. Qualifications Bachelor's degree in Computer Science, Data Science, Statistics, Mathematics, Physics, Economics, Engineering, or another quantitative discipline. Strong proficiency in Python, particularly Pandas, NumPy, Scikit-learn, Seaborn, and Matplotlib. Strong proficiency in SQL, including JOINs, subqueries, CTEs, aggregations, and window functions. Strong knowledge of data cleaning, data wrangling, feature engineering, and data validation. Proficiency in handling data from different sources and formats, including CSV, JSON, SQL exports, and structured databases