Kanika Madan

I’m an Associate Data Analyst with experience building automated ETL pipelines, running data validation, and delivering analytical insights for decision-making. I work with large-scale datasets (1M+ records) to improve reliability and enable trustworthy reporting.

I use SQL, Python, and PySpark to process and transform data daily for analytics workflows. I perform null analysis, duplicate detection, reconciliation of aggregates, and transformation verification to catch issues early and keep analytical datasets consistent.

I’m also hands-on with exploration and anomaly detection to identify trends, anomalies, and operational drivers. I’ve built Tableau dashboards and automated reporting that reduced manual reporting effort by 40%, translating stakeholder requirements into scalable data solutions.

Beyond reporting, I’ve developed machine learning outputs for business use cases—like Credit Card Fraud Detection using Isolation Forest and Local Outlier Factor on highly imbalanced datasets. I’m comfortable with AWS-based data engineering workflows (S3, EC2, Load Balancer, Route53) to support end-to-end ingestion, processing, and analytics readiness.