Home

Chaitanya - Data Scientist

[email protected]

Location: , ,

Relocation: NO

Visa: H1B

PROFESSIONAL SUMMARY: Chaitanya Duvvuru (717) 441-4974 [email protected] Have 15+ Years of experience in designing and developing analytics applications using AI / ML, Cloud, IoT and Big Data Technologies in the Healthcare, Insurance, Banking, Manufacturing and Retail sectors. Have 6+ years of working experience in the descriptive, diagnostic, predictive and prescriptive analytics. Strong experience in Statistics, Text Mining, Time Series Analysis & Forecasting, Anomaly Detection, Optimization, Computer Vision, Natural Language Processing (NLP), Recommendation Systems, Geospatial Analysis, Regression, Classification & Clustering. Experience in Probabilistic graphical models like Bayesian Networks, HMM, MRF and MDP. Experience in applying Deep Neural Networks algorithms like GAN, CNN, RNN, LSTM, GNN, TCN, Transformers and Autoencoders. Good experience in conversational AI, Text Classification, Language models, Topic Mining, Sentiment Analysis, and Text Summarization. Strong experience in Object Detection, Semantic Segmentation, Instance Segmentation, Image Classification and OCR. Solving computer vision problems using tools like TensorFlow, Keras, PyTorch, OpenCV and scikit-image. Experience in programming using C, C++, R, Python, SAS and MATLAB. Experience in the parallel programming with GPU frameworks like CUDA (C++ and Python) and RAPIDS. Experience in creating analytical dashboards/reports using visualization tools like Tableau, Power BI. Experience in AI/ML tools such as Azure ML, Databricks, MLflow, AWS SageMaker, Google Colab, GCP Vertex AI. Developing analytical solutions on Cloud platforms such as AWS, Microsoft Azure, Google Cloud and Snowflake. Experience in Telemetry Data Analysis, Geospatial Data Analysis, Survival Analysis, Predictive Maintenance. Experience in Spark, Flink and Kafka frameworks to perform near real time and streaming analytics. Hands on experience in Enterprise search frameworks like Elastic Search. Have sound knowledge on Enterprise Architecture, Data Architecture and Design Patterns. EDUCATION: Master of Technology in Information Technology - Anna University - 2007 Bachelor of Technology in Electronics and Communication Engineering- JNTU -2004 PROFESSIONAL EXPERIENCE: Organization Duration Designation Cognizant Technology Solutions India Pvt. Ltd. May 2007- May 2010 Programmer Analyst UnitedHealth Group Information Services Pvt. Ltd. Jun 2010 - Aug 2016 Project Lead BA Continuum India Pvt. Ltd. (a non-bank subsidiary of Bank of America) Dec 2016 - Jun 2017 Lead Analyst Mercedes-Benz Research & Development India Pvt. Ltd. Jun 2017 - Jun 2019 Solution Architect Unilever Industries Pvt. Ltd. Jun 2019 Jun 2022 Lead Data Scientist Connvertex Technologies Inc. Jun 2022 Till Date Lead Data Scientist CERTIFICATIONS: Data Science Specialization Machine Learning Specialization Deep Learning Specialization Natural Language Processing Specialization Generative Adversarial Networks Specialization Reinforcement Learning Specialization Practical Time Series Analysis Text mining and Analytics Practical Data Science on AWS Cloud Machine Learning on Google Cloud Microsoft Azure Machine Learning Microsoft Azure Data Scientist Associate (DP-100) Statistical Techniques for Data Mining & Business Analytics The Raspberry Pi Platform and Python Programming Post Graduate Certificate in IOT and Smart Analytics The Arduino Platform and C Programming Agile Project Management TECHNICAL SKILLS: Programming Languages C, C++, Python, Scala, Java, R, SAS, MATLAB Deep Learning Frameworks TensorFlow, Keras, CNTK, Caffe, MxNet, PyTorch NLP Tools OpenNLP, OpenAI, NLTK, TextBlob, BERT, GPT-3, T5, ELMo, rasa, Tesseract Parallel Programming PyCUDA,cuDNN,RAPIDS,Ray,Dask,Celery, DeepSpeed, doParallel,Spark,Flink Computer Vision Tools OpenCV, SimpleCV, PIL, MoviePy, scikit-image, GAN, CNN, RCNN, YOLO, UNet, Data Analytics tools KNIME, DataIKU, Alteryx, Driverless AI, DataRobot, Pyspark, SparkR, FlinkML, Geospark, QGIS, ArcGIS, Tensforforce, gym, KerasRL, HyperBand, Hyperopt Visualization Tools Tableau, Power BI, D3.js, QuickSight, TensorBoard,Data Studio Python Frameworks Django, Flask, Pyramid, Ray, Dash, Dask, Streamlit Big Data Frameworks Hadoop, Spark, Flink, Kafka, Beam Search Frameworks Elastic Search, Solr Cloud Platforms AWS, Azure, GCP, Snowflake Azure components ADF, ADLS, Azure ML, Databricks, AKS, ACI, IoT hub, Cognitive services AWS components S3, EC2, Kinesis, Glue, Lambda, QuickSight, SageMaker, IoT Greengrass, lex GCP components Vertex AI, Dataflow, IoT Core, BigQueryML, Pub/Sub, Kubeflow,TFX, Dialogflow Databases NoSQL Databases : MongoDB, Cassandra, HBase, Redis, Neo4J, Titan SQL Databases: DB2, Oracle, MySQL, SQL Server DevOps Tools Jenkins, Git, Docker, Kubernetes, Maven, AirFlow Java Frameworks Servlets, JSP, EJB, JDBC, JMS, Log4J, Struts, Spring, Hibernate Scala Frameworks Spark, Scalatra, Play, Lift ETL Tools DataStage, Talend, Azure DataFactory, AWS Glue, Dataflow, Beam, and DataProc Scripting Languages Power Shell, Perl, Shell Script JavaScript Frameworks React, redux, Node.js, D3.js, mljs, Highcharts, chart.js, Plotly.js, Tensorflow.js, Keras.js, OpenCV.js, Natural PROFESSIONAL EXPERIENCE: Client: Unilever Duration: June 2019 to Till Date Role: Lead Data Scientist Project: Data Science Center of Excellence Description: Unilever is a British multinational consumer goods company with headquarters in London, United Kingdom. Unilever owns over 400 brands. Its products include food, condiments, cleaning agents, beauty products and personal care products. Unilever is one of the oldest multinational companies; its products are available in around 190 countries. Data Science Center of Excellence team s focus is to provide solutions to various complex Business Problems through advance Machine Learning techniques. Also, to research and develop global Machine Learning products that solves common business problems through predictive and prescriptive analytics solutions. Responsibilities: Worked as a Lead Data Scientist Product Industrialization in the Data Science Center of Excellence team. Providing predictive and prescriptive solutions to the business in the areas of Sentiment Analysis, Sales Forecasting, Customer Segmentation, Product Recommendation, Investment Optimization, Logistics Optimization, Demand Forecasting. Solving complex business problems and developing analytics products for Country Category Business Teams. Leading and Mentoring the Data Scientists on solving the complex business problems using Machine Learning and AI. Performing Data Preprocessing, Exploratory Data Analysis, Model Building, Hyper Parameter Tuning and Model Deployment. Leading the Data Science Enablement portfolio and driving innovation through machine learning in Unilever. Developing strategies for improving the productivity of data science teams through automated machine learning tools. Developing machine models using state of the art machine learning and deep learning algorithms. Developing the machine learning design patterns for deploying the Machine Learning pipelines on Data Science platforms. Developing Model Governance standards; Model versioning & archival, Data & Concept Drift Detection and model retraining. Defining the Productionization / Industrialization standards for analytics products on different data science platforms. Defining the standards for Data Science Central Repository that facilitate the exchange of reusable Data Science patterns. Organizing Data Science trainings on ML tools and technologies and share the best practices among the data scientists. Researching and Developing global Machine Learning products that solves complex business problems. Defining Data Science coding standards and best practices for deploying the data science code into production. Developing automated machine learning pipelines using Azure machine learning, ADF, ADLS, MLflow, AKS and Databricks. Model deployment and model monitoring using Azure machine learning platform. Environment: R, Python, Tensorflow, PyTorch, Keras, Azure ML Studio, AWS SageMaker, Databricks, MLflow, GCP Vertex AI, H2O Driverless AI, Git, Kubernetes, Docker, PySpark, SparkR, Power BI. Client: Mercedes-Benz Duration: June 2017 to June 2019 Role: Lead Data Scientist and Analytics Architect Project: Advanced Analytics & Big Data Center of Excellence Description: Mercedes-Benz is a global automobile manufacturer and a division of the German company Daimler AG. The brand is known for luxury vehicles, buses, coaches, and trucks. Advanced Data Analytics and Big Data Center of Excellence team s focus is to provide machine learning solutions to various business problems of Mercedes-Benz cars, trucks, buses, vans and finance. Responsibilities: Worked as a Lead Data Scientist and Analytics Architect in the Advanced Analytics & Big Data Center of Excellence team. Developing intelligent auto response systems using Text Mining and Natural Language Processing techniques. Research and develop new analytics products that assists in Advanced Driver Assistance Systems. Developing machine learning prototypes for common business problems in the Automotive domain. Developing prototypes for Autonomous Driving use cases using Computer Vision and Deep Learning Techniques. Providing machine learning solutions to various business problems of Mercedes-Benz cars, trucks, buses, vans and finance. Improving the latency of machine learning models by implementing machine learning solutions on GPUs. Developing scalable predictive analytic applications on cloud platforms using Spark framework. Organizing data science meetups to exchange best practices among the data science community. Developing machine learning based solutions for budling smart factories and industrial automation. Developing scalable design patterns for deploying batch and real-time analytics products on cloud platforms. Defining the Data Governance standards for exchanging the data between central data lake and product data lakes. Defining the security framework for data exchange between central data lake and external data sources. Designing and developing chatbots that assists the Mercedes-Benz and Daimler users. Applying Predictive modelling using machine learning and Deep Learning algorithms to solve complex business problems. Providing ML solutions using methodologies like Computer vision, Natural Language Processing, regression & classification. Developing event driven patterns for industrializing streaming analytics solutions with technologies like Flink, Kafka, Spark. Designing and developing near real time model consumption patterns using Spark and Kafka. Designing and developing deployment design patterns with technologies like Docker and Kubernetes. Developing event driven patterns for deploying streaming analytics solutions with technologies like Flink, Kafka, Spark. Building near real time/streaming analytics engines using event driven architecture with Kafka and spark technologies. Developing real time data analytics applications using SparkSQL & Data Frames and Spark Streaming. Environment: Keras, Tensorflow, PyTorch, Azure, D3.js, Databricks, OpenCV, SimpleCV, MoviePy, scikit-image, PyCUDA, Spring, cuDNN, KNIME, DataIKU, Alteryx, SparkR, PySpark, R, Python, Scala, MATLAB, Druid, Tableau, Flink, Kafka, Flask, Django, AngularJS, Node.JS, Geospark, QGIS, CARTO, Locale, Kepler.gl Client: Bank of America Duration: December 2016 to June 2017 Role: Lead Data Scientist Project: Consumer Banking Analytics Description: Bank of America is an American multinational banking and financial services corporation headquartered in Charlotte, North Carolina. It is the second largest bank holding company in the United States by assets. Consumer Banking Analytics team s focus is to build analytical models for the consumer banking domain. Responsibilities: Worked as a Lead Data Scientist in the Consumer Banking Analytics team. Developing machine learning solutions for interactive response systems such as chatbots. Mining the text data to discover trending topics and finding sentiments of consumers on consumer banking products. Developing machine learning models for consumer banking domain. Analyzing the consumer spend and providing alerts for customer segmentation, forecasting, Regression and classification. Analyzing the consumer spend patterns from the terabytes of customer transactional data and offer recommendations. Solving business problems through machine learning tools and technologies. Understand business problems and provide analytical solutions for making better decisions. Developing Analytical dashboards to visualize and analyse the consumer data. Machine Learning Activities like Data Cleansing, Imputing and preparing the data for modeling and analysis purposes. Exploratory data analysis on the customer transactional data using R and Python. Creating Dashboards in tableau to summarize/visualize real time streaming trends/events. Developing machine learning models to improve the consumer experience by offering investment recommendations. Environment: R, Python, NLTK, Tableau, SparkR, PySpark, SQL. Client: UnitedHealth Group Duration: June 2010 to August 2016 Role: Technical Lead and Architect Project: Consumer Database Development Description: United Health Group is the most admired Health Care Company in the United States of America. UHG maintains its membership information in the Consumer Database application. It is a single repository to store demographic, eligibility, coverage, benefits, market and accounting information of all the members across all applications in United Health Group Line of Business. Consumer Database is a modern application developed to provide user real time analytics and dashboards to senior management and business analysts to take effecting business decisions. This initiative led to innovation, reduce fraud and improve patient care in a competitive Healthcare marketplace. Responsibilities: Worked as a Technical Lead and Architect in the Consumer Database development team. Developing the architecture for automating the end-to-end data flows using big data technology stack. Developing design patterns for automating data flows from legacy systems to Big Data. Developing low latency API services that fetch data from Elastic Search servers. Working on proof of concepts to build Machine Learning models using big data tools. Developing data pipelines for importing and exporting data on Big Data cluster. Generating vendor feeds using Hive on Big Data Cluster. Developing parser and loader map reduce application to retrieve data from HDFS and store them to HBase and Hive. Importing the structured data from databases into the HDFS using Sqoop and the unstructured data using Flume. Exploring with the Spark improving the performance and optimization of the existing algorithms in Hadoop using Spark Context, Spark-SQL, Data Frame, Pair RDD's, Spark YARN. Migrating Hive QL queries on structured into Spark QL to improve performance Developing Spark code using Scala. Used Spark-SQL and Spark-Streaming for faster processing of data. Performing transformations, cleaning and filtering on imported data using Hive, Pig, MapReduce and Spark. Developing predictive analytic applications using Apache Spark MLIB APIs using Scala and Python. Using Talend to generate vendor feeds from HDFS using Talend open Studio. Responsible for defining the data flow within Hadoop eco system and direct the team in implement them. Working on the analytics product to detect and eliminate fraudulent claims using SparkR and PySpark. Writing Pig scripts to parse the data and built JSON documents and to store them on Elastic Search servers Developing near real time analytic applications using Kafka and Spark frameworks. Creating a Big Data pipeline that transfers and lot of data each day using Apache Kafka and Hadoop. Automating data transformation; facilitating the data cleansing and performing Real-time Analytics using R and Spark MLib. Parsing high-level design spec to simple ETL coding and mapping standards. Scheduling Job sequence, parallel, server jobs and UNIX scripts using TWS/d. Designing and developing Parallel and Server jobs in DataStage Designer creating jobs, data mapping, data extraction, transformation and loading. Working directly with Business for gathering requirements and delivering Tasks. Writing Shell scripts to preprocess the input files and output files. Working on API development using Spring Framework with MVC design pattern. Designing and developing the User Interface using JSP, HTML, CSS and JavaScript. Designing and implementing Singleton, Service Locator, Facade, and Proxy Design Patterns. Developed and used SOAP and RESTful Web services for sending and getting data from different applications. Doing UI and Server-side development and implementation using Core Java, Spring, Web Services, and XML Spring MVC was used to communicate the Flex and the Back-end mainframe application Setting up the infrastructure for accepting HIPAAI 834 files from customers. Developing WTX maps for converting HIPAAI 834 format to Gateway Standard format to process files in EEMS. Configuring MQs and working on message sets for mapping XML to COBOL formats using WMB. Designing and implementing Service Locator, Facade, and Proxy Design Patterns. Using Hibernate and JMS to send data on Message queues to update DB in backend DB2. Using Java Frameworks used are Struts, Hibernate, and Spring. Used Log4J for logging. Using JUnit framework for unit testing of application and Maven to build the application and deployed on Web. Environment: MAPR, Sqoop, Pig, Hive, HBase, MapReduce, Talend, Tableau, Spark, Kafka, Elastic Search, Python, COBOL, JSP, EJB, JPA, JMS, JAX-WS, JAX-RS, R, SAS, Spring, Java, AJAX, DB2, Maven, WMQ, jQuery, Servlets, JSP, EJB, JMS, Spring, Hibernate, Struts, WTX, WMB, WMQ, HTML, CSS, XML, JavaScript, Tortoise SVN, Maven, DataStage, Talend, UNIX Shell Scripts, TWS, Oracle, Q replication. Client: Sallie Mae Duration: December 2009 to May 2010 Role: Senior Developer Project: Sallie Mae Eagle 2 Enhancement & Maintenance Description: Sallie Mae used to be a Government Sponsored Enterprises (GSE) of the US Federal government; Sallie Mae is in the business of providing Students Loans to eligible borrowers, based on the framework provided by the US Department of Education and the Federal Government. Sallie Mae envisages positioning itself as the provider of a common platform to facilitate the communication and transaction (Translator and Router) between the primary participants of the Student Loans industry namely: Student, Schools, Lenders, Guarantors. The Eagle II applications supported are Customer Information (CI), LA (Loan Approval), ALM (Account Loan Maintenance), Lender Funds Management (LFM). Responsibilities: Worked as a Senior Developer in the Sallie Mae Eagle 2 Enhancement & Maintenance team Responsible for the design, coding and unit testing of modules. Analysis and defects with the optimal solution. Preparing the Low-level Design of the modules. Client: MetLife Duration: May 2008 to November 2009 Role: Senior Developer Project: MetLife UDS Customer Support Description: UDS, Unified Disability System, is MetLife s comprehensive disability claims management system. This system supports the STD (Short Term Disability) and LTD (Long Term Disability) and comprehensive STD/LTD business of MetLife with annual premiums of $1 billion. STD is for a period of less than twenty-six weeks, while LTD can extend over a period of many years. UDS generates some two million checks/EOBs and insured/customer correspondence yearly. Within UDS, there are myriads of embedded subsystems like online diaries, online benefit calculations, electronic duration guidelines, reserves trails, electronic data interchange, traditional feeds to the MetLife accounting systems (MetFacs), check-writing, EFT (Electronic Funds Transfer) etc. Responsibilities: Worked as a Senior Developer in the MetLife UDS Customer Support team. Developing the code for business requirements and delivering zero defect code. Responsible for High Level and Low-level Design of the core modules. Gathering project requirements from business and delivering tasks. Preparing Technical Design Documents and Design Review Power Points. Maintaining the E-tracker Tool to track the Quality of Delivery. Client: MetLife Duration: May 2007 to April 2008 Role: Developer Project: MetLife LTC Maintenance Description: MetLife has used an insurance product INGENIUM from Insurance Solutions Corporation (SOLCORP). LTC deals with developing a Total Long-Term Care System for MetLife. The sub systems maintained in LTC are: A) Plan Maintenance Facility B) Enrollment & Underwriting C) Benefit Authorization D) Claims E) Billing Interfaces F) Reporting Responsibilities: Worked as a Developer in the MetLife LTC Maintenance team. Developing new modules for many processes and generated IO Modules for the Cobol programs Handling different business processes and Involved in Low-level Design and Coding of the modules Analyzing defects and fixing the defect with the optimal solution Providing the Production support for LTC Batch Trial Place: South Jordan, Utah, USA Date : CHAITANYA DUVVURU Keywords: cprogramm cplusplus continuous integration business analyst artificial intelligence machine learning user interface javascript business intelligence sthree database rlang information technology Louisiana