Data Science Machine Learning

SANJANA KADAMBE MURALIDHAR

Arlington, VA *******.**********@***.*** 571-***-**** LinkedIn GitHub Portfolio EDUCATION

George Washington University Washington DC

Master of Science, Data Science (GPA: 3.9) May 2026 Coursework: Data Science, Data Mining, Data Warehousing, Machine learning, Cloud Computing, Data Visualization SJB Institute of Technology Bengaluru, India

Bachelor of Engineering, Information Science August 2022 TECHNICAL SKILLS & CERTIFICATIONS

• Programming & Databases: C, Python, R, MySQL, MongoDB

• Libraries: NumPy, Pandas, SciPy, Matplotlib, Seaborn, Plotly, streamlit, Scikit-learn, TensorFlow

• Data Engineering & Cloud: Informatica, AWS

• Visualization & Business Intelligence: Tableau, Power BI, Excel (Pivot Tables, VBA)

• Key competencies: Statistics, Data integration (ETL), Cloud data migration, Data Modeling, Data analytics and visualization, Data Warehousing, Consulting, Automation, Problem-solving, Collaboration and teamwork, Adaptability

• Certifications: Informatica Data Integration and Data Quality R41 certified Professional, IBM Data science Professional. PROFESSIONAL EXPERIENCE

Data Science for Sustainable Development, Washington DC October 2024- Present Data Science Researcher

• Established sustainability benchmarks by creating a city-specific eco-label for 50+ university buildings through data modeling, preprocessing, and analysis of energy and environmental data.

• Enhanced stakeholder decision-making by developing dynamic Power BI dashboards and a Streamlit app to visualize energy and environmental metrics, driving actionable insights with improved efficiency.

• Deployed machine learning models to forecast energy demand with 91% accuracy, enabling proactive resource allocation and reducing energy waste by 16%.

Informatica, Bengaluru

Analyst- Consultant August 2022 – July 2024

• Enhanced data-driven decision-making by designing ETL pipelines using Informatica workflows, improving data transformation accuracy and efficiency by 40%, and achieving a CSAT rating of 4.7.

• Increased data processing efficiency by 50% by optimizing ETL workflows in Informatica Cloud Service, leveraging Amazon S3 and Redshift for seamless Oracle data migration.

• Reduced incident resolution time by 25% by developing a real-time Power BI ETL performance dashboard, tracking latency, error rates, and workflow efficiency across 500+ processes.

• Automated ETL workflow optimization by implementing SQL-based transformation rules, reducing query execution time by 40% and improving cloud data pipeline performance.

• Implemented a Python-based outlier detection algorithm to identify and resolve anomalies in 1M+ records, improving data quality by 90%, reducing processing errors, and enhancing system reliability.

• Developed a CLI-based certificate generation tool using Python, automating trusted certificate creation, enabling secure data transfer during Cloud data integration-Power Center upgrades, and eliminating manual errors in SSL/TLS configuration. Verzeo, Bengaluru

Data Analyst and Machine Learning Intern February 2020- March 2020

• Improved data-driven decision-making by automating Tableau dashboards for performance tracking, resulting in a 30% increase in reporting accuracy and reduced manual data processing using Pandas, NumPy, and TensorFlow. PROJECT EXPERIENCE

Spotify Global Music Analytics: Analyzed Spotify records to classify song popularity with 93% accuracy using Random Forest, uncovering cultural preferences, seasonal trends, and global-local distinctions through clustering, PCA, and statistical analysis. Market Dynamics and Consumer Insights from Steam Game Analytics: Executed a comprehensive analysis of Steam’s game library using advanced analytics, clustering, and predictive modeling (XGBoost, LightGBM), uncovering key trends in pricing, popularity, and player behavior, driving actionable insights into market dynamics and consumer preferences. Nutrition Analysis Dashboard: Developed an interactive Power BI dashboard to analyze meal patterns, visualizing calorie and nutrient intake while identifying trends in unhealthy eating habits, enabling data-driven dietary recommendations. Used Car Price Prediction Model Development: Developed a Used Car Price Prediction Model leveraging Python and machine learning algorithms (Linear Regression, Decision Tree, KNN, Random Forest), achieving 85% accuracy with Random Forest.

Contact this candidate