Machine Learning Data Analyst

YASHASWANI JONNALAGADDA

Boston, MA 857-***-**** *********************@*****.*** LinkedIn GitHub PROFESSIONAL SUMMARY

● Data Scientist with 4+ years of experience applying machine learning, data visualization (Power BI, Tableau) and statistical analysis to solve complex problems across finance, healthcare, and telecom industries. Proficient in Python, SQL, and cloud platforms

(AWS, GCP), with hands-on experience developing predictive models, automating validation pipelines, and deploying ML solutions using PySpark and SageMaker.

● Skilled in extracting insights from large-scale datasets (6GB+), optimizing storage with Parquet in S3, and building interactive dashboards in Tableau and Power BI for data storytelling and executive decision-making.

● Strong track record in end-to-end model development, from data wrangling to deployment, delivering measurable improvements in accuracy, efficiency, and business outcomes.

WORK EXPERIENCE

CME Group

Data Analyst Aug 2024 – Mar 2025

● Investigated and resolved data discrepancies in trading volume reports by validating metrics across Snowflake, BigQuery, and partner APIs using advanced SQL and Python scripts.

● Rebuilt legacy Alteryx workflows using dbt and standardized transformation logic across PostgreSQL and BigQuery, improving data consistency.

● Developed a multi-threaded Python validation engine incorporating machine learning algorithms and PySpark to automate large- scale data comparison, reducing issue detection time by 85%.

● Deployed automated discrepancy detection via Docker containers on Kubernetes, enabling scalable, event-driven validation pipelines.

● Created dynamic Tableau dashboards to visualize anomaly trends and support executive decisions, reducing manual reporting efforts by 80%.

Omni Healthcare

Data Analyst Jan 2022 – Aug 2023

● Collaborated with clinical teams to understand business needs and streamline healthcare data workflows for improved analytics.

● Built scalable ETL pipelines using AWS Glue and EMR to process high-volume EHR data from MongoDB; ensured clean, validated datasets using Python.

● Designed optimized Parquet-based data models in AWS S3, reducing storage costs by $16K–$24K annually and accelerating query performance.

● Automated ETL workflows with AWS Step Functions and EventBridge, enabling 24/7 data availability and reducing manual effort by 90%.

● Developed Power BI dashboards using advanced data visualization techniques and statistical modeling to deliver operational insights, supported ML deployment in SageMaker for readmission risk prediction, and applied NLP on clinical notes for improved feedback analysis.

● Developed and implemented predictive modeling techniques using machine learning algorithms to forecast patient readmission rates, improving accuracy by 35%.

BSNL Pvt. Ltd

Data Analyst Aug 2019 – Dec 2021

● Developed automated data quality checks using Python in AWS Lambda, reducing processing errors by 50% for telecom usage data stored in Amazon S3.

● Designed and implemented robust data pipelines using Informatica BDM, managing data ingestion into Amazon S3 Data Lake and optimizing data type conversions and SCD loads, improving data processing efficiency by 40%.

● Designed executive dashboards in Tableau, translating telecom and subscriber datasets into actionable insights for BSNL leadership. SKILLS

Programming Languages: SQL, Python (Pandas, NumPy, Scikit-learn, TensorFlow), Scala, PySpark Databases: PostgreSQL, Microsoft SQL Server, MySQL Big Data Technologies: Hadoop, Hive, Apache Spark, Apache Kafka, MapReduce Data Skills: ETL, A/B Tests, PostgreSQL, Apache Spark, NoSQL, Salesforce, SaaS, JIRA, Data Analysis, Querying, testing, Statistical methods, Data pipeline, Data Mining Cloud Technologies: AWS (S3, DynamoDB, Lambda, Redshift), Azure, Snowflake, Databricks, Airflow EDUCATION

Northeastern University, Boston, MA Master of Science in Information systems Sreenidhi Institute of Science & Technology, India Bachelor of Technology in Electronics and Communication Engineering

Contact this candidate