Data science in healthcare is a growing area within the industry. Data scientists in this TalentCloud should have worked with healthcare data such as medical claims, EMRs, and other related data that can solve important problems in the industry. This TalentCloud requires 2+ years of experience with analyzing data related to healthcare/pharma.
Required Skills
- Proficient in Python/ R and SAS/ STATA
- Working knowledge of health care systems and healthcare terminology
- Experience with claims data
- 2+ years of experience in the healthcare industry or a related field.
- 2+ years of experience with NLP/NLU and computer vision
- Extensive experience with scikit-learn, statsmodels, SciPy, Keras, PyTorch, and TensorFlow or similar packages in R
- Expert in supervised (classification, regression) and unsupervised machine learning (anomaly detection, cluster analysis)
- Proficient in building/ tuning/ testing models using machine learning and deep learning algorithms including tree-based methods, Bayesian models, support vector machines, feed forward networks, recurrent neural networks, and convolutional neural networks
- Extensive experience with feature engineering and dimensionality reduction methods
- Expert in pre-processing data including dealing with anomalies and outliers, dealing with missing values, flooring/ capping, and data transformations.
- Hands-on experience writing data processing and data pipeline for structured and unstructured data model development
- Expert in statistical models such as regression analysis, survival analysis, and time series analysis
- Proficient in SQL
- Excellent communication and storytelling skills
- Comfortable working independentlyFamiliarity with version control, especially Git/GitHub
- Understanding of HIPAA and the importance of patient data privacy
Preferred Skills
- Graduate degree or foreign equivalent in Statistics, Applied Statistics, Economics, Computer Science, or another related quantitative field
- Experience with econometric models such as panel data analysis and vector autoregression
- Experience with Apache Spark
- Experience with NoSQL databases
- Experience with Django
- Experience with Containers
- Experience in cloud platforms such as GCP, AWS, or Azure
