Pranav Sreevatz Natarajan

Detail-oriented Data Analyst with strong expertise in data visualization, data analysis, and transforming complex data into actionable business insights. Skilled in leveraging analytical frameworks and Agile and Scrum methodologies to enhance project outcomes and decision-making efficiency. Proficient in applying Machine Learning (ML) and Artificial Intelligence (AI) concepts to uncover trends, optimize performance, and drive innovation. Recognized for declarative thinking, effective team collaboration, and clear communication across technical and non-technical stakeholders.

• Earned Machine Learning Certification through a focused Data Science Workshop.
• Completed IEEE Computer Science hackathon.
• Engaged in numerous IT symposiums at reputed colleges across India, expanding both knowledge and professional network.
• Earned AWS Cloud Practitioner Certification as of 11/30/24.
• Earned Certified Scrum Master certification as of 07/07/24.

• Data Analytics & AI Research Projects – Participated in academic and applied projects involving predictive modeling, data visualization, and machine learning solutions.
• Hackathons & Case Competitions – Engaged in analytics and business strategy challenges, showcasing teamwork and innovative analytical thinking.
• Professional Associations – Active member of IEEE Data Science from 2019-2021.
• Singing - Won numerous singing competitions since age 8, and claimed 4th place in a National level singing competition.
• Public Speaking / Debate Club Member – Recognized for strong communication and presentation skills during intercollegiate events.

• Earned AWS Cloud Practitioner Certification as of November 30 2024.
• Earned Certified Scrum Master certification as of July 7 2024.

Predicting Frog Presence Using Machine Learning                      Jan 2025 - May 2025

 • Collaborated on a predictive model for identifying frog species presence in southeastern Australia using remote-sensed climate data  and Planetary Computer datasets.  

• Performed extensive feature engineering (sin transformations, log normalization, water availability metrics) and optimized hyperparameters across models like Random Forest, Gradient Boosting, and Logistic Regression. 

• Designed ensemble models that boosted test F1 score to 0.8056, validated through 5-fold cross-validation and SHAP analysis for interpretability.  • Contributed to final insights for ecological conservation by identifying priority habitats and climatic indicators (e.g., lat_sin, lon_sin,  and TDIFF) with highest predictive impact. 

Crime Prediction and Detection                                                     Dec 2021 - Mar 2022

• Devised software integrating Machine Learning, KNN algorithm, and SQL to anticipate crime rate and analyze crime patterns.

• Enabled precise location and pattern detection, facilitating effective crime-solving approaches for law enforcement agencies.

• Augmented crime-solving efficiency by 25%, providing actionable insights and clear procedural paths.