Chetan Chauhan

• Streamlined complex SNP genotype data analysis algorithms, enhancing efficiency and accuracy in genomic research. • Integrated machine learning techniques to predict significant genetic sequences, significantly speeding up the data analysis process. • Contributed to a groundbreaking approach in genomic data analysis, paving the way for significant scientific discoveries and insights. • Grateful for the mentorship of Professor Justin Kennedy, advancing the future of genomic research and understanding of complex diseases.

Worked for Hyundai Capital America as a client, where I led critical data projects that streamlined processes and enhanced efficiency. • Spearheaded the ETL migration to AWS Cloud Data Warehouse using PySpark, improving data pipelines for ML applications. • Directed project architecture, optimized Redshift tables, developed Glue jobs, and automated processes, reducing processing time by 23%. • Leveraged AWS Glue, Redshift, and CloudWatch for efficient data processing, automation, and monitoring, providing real-time data insights and ensuring robust data workflows. • Collaborated with QA to automate ETL testing using Apache Airflow, reducing testing time and costs, and ensuring timely project delivery.

Worked for U.S. Polo Assn. as a client, where I played a pivotal role in data analysis and ETL process optimization. • Worked with ETL developers to translate business requirements into precise ETL job specifications, documenting data mappings, dictionaries, and lineage diagrams to ensure integrity of data assets using Snowflake and Star schema. • Utilized Oracle SQL Developer Data Modeler for comprehensive data modeling, creating logical and physical data models that supported diverse business processes and analytical needs. • Successfully migrated DataStage jobs to AWS Data Pipelines, designing and implementing strategies for complex ETL processes using S3(Bucket policies, Lifecycle policies), Glue, Lambda, Python, and MongoDB, ensuring seamless transition and minimal disruption to business operations. • Assisted the QA team in running tests to ensure business rules on transformed data and ETL processes, utilizing JIRA for tracking.

• Conducted cutting-edge ML research as a research assistant at Northeastern University, focusing on estimating the dimension of the latent manifold of the MNIST Digits dataset using UMAP, a dimensionality reduction technique. • Demonstrated expertise in evaluating clustering algorithms and determining the optimal number of clusters using external indices and statistical methods. • Pre-processed large volume datasets, performed Apache Hive for analysis and querying of big data, Pig for data transformation, and R language to visualize the data as part of a sport analysis project. • Developed test plans to improve the processing of data by adding Machine Learning Algorithms to evaluate more accurately, resulting in a significant increase of 42% reliable data of players for the team management.