Riya Marathe

Results-driven Data Scientist with hands-on experience in data collection, data cleaning, preprocessing, and exploratory data analysis (EDA). Proficient in Python (NumPy, Pandas, Scikit-learn, Matplotlib/Seaborn) with expertise in supervised and unsupervised machine learning algorithms including regression, classification, clustering, and time-series modeling (ARIMA). Skilled in collaborating with cross-functional teams, preparing data visualizations, and documenting processes for clear stakeholder communication.

Familiar with GenAI concepts, prompt engineering, and LLM API integrations. Passionate about leveraging data to drive innovation and optimize business performance.

Associate QA Engineer – AI & Data Quality at Numerator (2025-11 – Present)

• Collected and standardized large-scale consumer panel time-series datasets; performed data cleaning, preprocessing, and EDA to ensure accuracy and consistency for ML model inputs.
• Built and evaluated machine learning models (classification, regression, anomaly detection) using Scikit-learn; tracked performance with Accuracy, Precision, Recall, F1-Score, RMSE, and MAE.
• Implemented feature engineering pipelines using Pandas and NumPy; applied statistical sampling, distribution analysis, and outlier detection to support predictive analytics workflows.
• Developed Python algorithms for root cause analysis and KPI monitoring; automated ETL pipeline tasks to improve data integrity and reduce manual intervention.
• Collaborated cross-functionally with senior engineers and SMEs to define success metrics, resolve data inconsistencies, and document data collection processes for stakeholder reporting.
• Maintained Git-based version control for all workflows; ensured GDPR-compliant data handling across all pipelines.

Data Science Intern at YBI Foundation (2024-01 – 2024-12)

• Developed and evaluated supervised and unsupervised ML models (classification, regression, time-series) using Python; documented success metrics for stakeholder review.
• Conducted EDA, statistical analysis, and feature engineering on structured datasets; identified distributions, outliers, and trends to support data integrity and algorithm development.
• Translated technical model results into clear data visualizations and reports using Matplotlib/Seaborn and Excel to support business decision-making.

MBA in Information Technology – Bharati Vidyapeeth University, Pune

BCA in Bachelor of Computer Applications – Parul University, Vadodara

BSc – North Maharashtra University