• Bring machine learning models, AI Process Automation models and code into production together with a multi-disciplinary team of data scientists, software development engineers, and subject domain experts.• Developed Neural Network based predictive model and risk analytics, utilizing large amounts of structured and unstructured data • Ensure the Machine Learning code, models and pipelines are deployed successfully into production, and troubleshooting issues that arise.• Performed A/B testing, market research, analysis, campaign planning, and strategic plans for solving complex healthcare problems• Used Pandas, Numpy, Scipy, Matplotlib, Sci-kit-learn, and NLTK in Python for developing various Machine learning algorithms.• Automated model training, testing and deployment via machine learning continuous delivery pipelines ( CI) • Established criteria for evaluating algorithm performance and suitability• Keep up to date with Machine Learning best practices and evolving open source frameworks such as Keras, Tensorflow, Scikit-learn, Theano, Caffe (ConvolutionalArchitecture for FastFeatureEmbedding) ,Torch• Implemented PySpark jobs for batch processing to handle massive volume of data from various data sources - Bloomberg, Government publications, unstructured news articles, etc. and data persisted in HDFS. Configured a CI/CD pipeline in Kubernetes and Docker Swarm.

• Developed a predictive model for detecting recovery (subrogation) opportunities for Worker's Compensation claims.• Used Natural Language Processing (NLP) to analyze claim diaries, which supplemented various structured data.• Designed spell-correction and abbreviation-disambiguation tools for cleaning and structuring textual data.• Enhanced text-mining algorithms for broader use within the company for predictive model building• Worked with business users, business analysts, program managers, project managers, system analysts for reviewing business requirements• Developing and executing multiple proof of concepts of the cutting-edge technologies in the field of AI/ML, data lake, data warehouse, big data, self-service analytics, data discovery and helping with roll-out & adoption of selected technologies to enable business value• Developed multitude of Machine Learning algorithms such as customer segmentation, Support Vector Machine, XGBoost to improve Insurance agent’s engagement with customers and developed marketing mix model • Trained Data with Different Classification Models such as Decision Trees, Random forest, Support Vector Machine models to classify quartiles & predict scores