HARSH MAHESHKUMAR PANDYA
Whitestown
Summary
Results-driven Data Scientist with extensive experience in complex predictive modeling, data analysis, and advanced statistical techniques, dedicated to uncovering actionable insights that drive strategic decision-making. Proficient in leveraging machine learning models to address real-world challenges and optimize business outcomes across diverse industries. Committed to continuous improvement and innovation, ensuring the delivery of impactful solutions that align with organizational goals. Passionate about transforming data into meaningful narratives that foster growth and efficiency.
Overview
5
5
years of professional experience
1
1
Certification
Work History
Data Scientist
Humana
06.2025 - Current
- Collaborated with multidisciplinary teams, including software engineers, data architects, and business analysts, to define data requirements and align business objectives with scalable, actionable data-driven solutions.
- Designed and implemented statistical models to analyze the causal effects of benefits interventions on investment outcomes supporting $50M investment.
- Utilized Power BI to construct dashboards that visualize year-over-year and week-over-week impacts, focusing on compliance trends and gap closures for multiple HEDIS measures.
Data Scientist
Indiana University Athletics
10.2022 - 05.2025
- Optimized recruitment with performance dashboards for United States Olympic and Paralympic Committee (USOPC), enhancing athlete readiness for the Paris Olympics by 25% in 9 months
- Visualized athlete performances by developing three interactive dashboards using ZOHO Analytics to track 10+ KPIs for 300+ athletes across the U.S., significantly streamlining decision-making for training and competition strategies
- Enhanced training efficiency by 50% by creating a Python based data pipeline to extract and process over 1 million raw records using Selenium and SQL, delivering daily insights for optimized and data-driven training programs
Machine Learning Associate - Intern
Infosys Springboard
02.2022 - 05.2022
- Collaborated with stakeholders using Agile to define project goals, ensuring faster iteration cycles and seamless collaboration
- Executed a custom algorithm using Python and OpenCV to generate 5,000+ synthetic images, reducing model loss by 40%
- Conducted user testing and feedback sessions with individuals affected by color vision deficiency to refine the model's usability
- Implemented a deep learning solution using Tensorflow to address accessibility challenges for individuals with color vision deficiency, collaborating with cross-functional teams and healthcare experts to align with user needs
Machine Learning Engineer - Intern
AirBorne Tech
04.2021 - 07.2021
- Conducted data and root cause analyses, driving improvements in product development, performance, and optimization
- Mentored 4 new hires in data annotation processes and collaborated with subject matter experts to gather project requirements
- Improved car damage detection models by implementing advanced data preprocessing strategies using Python and fine-tuning the model architecture using Detection and Google Cloud Vision API, boosting accuracy by 4%
- Facilitated teamwork and communication to optimize processes and enhanced customer experience through ML solutions, cutting insurance claim processing time by 60%
Education
Master of Science - Data Science
Indiana University Bloomington
USA05-2024
Bachelor of Science - Information Technology
University of Mumbai
India06-2022
Skills
- Data Science and Machine Learning: Python, R, SQL, Tensorflow, PyTorch, Pandas, Numpy, Scikit-Learn, Natural Language Processing, Deep Learning, Computer Vision
- Data Engineering: SQL Databases (Postgresql, Mysql, SQL Server), Nosql Databases (Mongodb), ETL Tools (Apache Airflow)
- Business Intelligence: Tableau, Power BI, Data Visualization (Matplotlib, Seaborn, Plotly), KPI Reporting, Dashboard Creation, Data Storytelling
- Cloud Computing & Big Data: AWS, Azure, PySpark, Databricks
- Version Control & Collaboration: Git, Docker, Kubernetes, CI/CD
- Advanced Analytics and Statistical Modeling: Regression Analysis, Ensemble learning (Bagging, Boosting), Statistical Process Control, Root Cause Analysis
- Automation and Scripting: Bash, Python, Automation Scripting, Devops
- Machine Learning Operations (Mlops): Model Deployment, Model Monitoring, Model Validation, Continuous Integration For Models
- Data Management and Processing: Data Cleaning, Wrangling, Transformation, Aggregation, Data Pipelines
Certification
- Applied Data Science with Python Specialization - University of Michigan
- Deep Learning Explained - Microsoft
- Data Science : Visualization - HarvardX
Timeline
Data Scientist
Humana
06.2025 - Current
Data Scientist
Indiana University Athletics
10.2022 - 05.2025
Machine Learning Associate - Intern
Infosys Springboard
02.2022 - 05.2022
Machine Learning Engineer - Intern
AirBorne Tech
04.2021 - 07.2021
Bachelor of Science - Information Technology
University of Mumbai
Master of Science - Data Science
Indiana University Bloomington