NIHARIKA S.
Mid-Level Data Analyst
Open to offersNew to PlatformAbout
Niharika S. is an accomplished Data Analyst with over three years of experience specializing in the financial services and pharmaceutical sectors. Her expertise lies in transforming large-scale enterprise datasets into significant insights that drive cost efficiency and strategic decisions. At JPMorgan Chase & Co., she developed a real-time anomaly detection pipeline using Python and AWS Redshift, identifying over $4.2 million in potential fraud in its first quarter of operation. Niharika also optimized risk reporting processes which resulted in substantial time and cost savings. Her work at Cipla Ltd. included engineering demand forecasting models and automating clinical trial data pipelines, which significantly enhanced operational efficiency and reduced costs. She holds a Master of Science in Computer Science from Purdue University Northwest, and her technical proficiencies include SQL, Power BI, and cloud platforms like Amazon Web Services and Snowflake, showcasing a robust command of ETL pipelines, machine learning, and data warehousing.
Experience
Data Analyst
JPMorgan Chase & Co. USA · 2025 — PresentDesigned and implemented a real-time transaction anomaly detection pipeline using Python and AWS Redshift, identifying potential fraud exposure. Consolidated risk reporting from 12 data sources into a single Power BI dashboard, significantly reducing the reporting cycle. Improved performance by refactoring over 40 SQL queries within the Snowflake enterprise data warehouse. Developed a customer segmentation model in Python for targeted marketing initiatives. Migrated critical financial datasets to an AWS S3 and Glue ETL architecture while ensuring SOX compliance. Established automated data quality validation frameworks, effectively reducing reporting errors. Created KPI scorecards synthesizing loan performance and deposit flow data to aid capital allocation decisions.Data Analyst
CIPLA Ltd. India · 2021 — 2023Developed a demand forecasting model in Python that integrated multiple sales and market variables to reduce stockouts. Automated the ingestion of clinical trial data pipelines using SQL and Python to enhance data preparation efficiency. Created Tableau dashboards to monitor supply chain KPIs, assisting procurement in reducing raw material overstock costs. Conducted statistical root-cause analysis on production batch failures to identify critical process variables and enable corrective measures. Standardized master data management protocols, improving data accuracy and regulatory submission integrity.
Skills & Expertise
Education
- Master of Science (M.S.) in Computer SciencePurdue University Northwest · — — 2025