About
Highly analytical and results-driven B.Tech student specializing in Data Engineering and Machine Learning, with hands-on experience in developing predictive ML models, building robust ETL pipelines, and designing scalable data warehouses. Nayan consistently delivers solutions that enhance data accuracy, optimize operational efficiency, and drive data-driven decision-making for enterprise partners.
Work
Jaipur, Rajasthan, India
→
Summary
As a Data Engineering Intern, Nayan developed and deployed machine learning models and ETL pipelines, delivering business intelligence solutions that optimized data accuracy and accelerated decision-making.
Highlights
Developed machine learning models for client churn prediction with 82% accuracy, analyzing 15,000+ subscriber records to reduce retention costs by 25% for enterprise partners.
Engineered ETL workflows using Python and SQL to transform 50GB+ transaction datasets from 8 diverse sources, reducing execution time from 6 hours to 45 minutes through optimized data warehouse strategies.
Enhanced model prediction accuracy from 75% to 82% over 3 iterations through iterative feature engineering and hyperparameter optimization techniques.
Deployed orchestration workflows using Apache Airflow to streamline validation and transformation routines, monitoring 12 daily quality checks across production environments.
Collaborated with management teams to define requirements and developed 4 Power BI dashboards, providing business intelligence reports that accelerated weekly analysis cycles for senior leadership by 3 hours.
Skills
Programming Languages
Python, Java, SQL.
Cloud Platforms & Services
GCP, Snowflake, Databricks.
Frameworks & Big Data
Flask, Django, FastAPI, Apache Spark, Apache Airflow, Apache Kafka.
Data Science & ML Libraries
NumPy, Pandas, Scikit-learn, Matplotlib, Plotly, Seaborn.
Database Technologies
MySQL, PostgreSQL, MongoDB, Snowflake, Data Modeling.
Visualization & BI Tools
Looker, Power BI.
Development & Analytics Tools
Git, Jupyter, Databricks, Shell/Bash, Version Control.
Projects
SwiggyXSnowflake End-to-End Analytics & Data Warehousing Solution
Summary
Established a scalable Snowflake data warehouse architecture, integrating staged, clean, and consumption layers to handle 120,000 order transactions across 18 restaurants in South Delhi, serving 150+ clients, and implementing star schema modeling and SCD2 history tracking.