Chicago, Illinois, United States
With a Master of Science in Information Science from the University of Illinois Urbana-Champaign, I serve as a Data Scientist at COUNTRY Financial®, where my core competencies include large-scale data processing and advanced analytics using Python and SQL. My educational journey fortified my expertise in data science, enabling me to build and optimize data pipelines and deliver actionable insights through in-depth data analysis. At COUNTRY Financial®, our team optimized data retrieval processes, significantly reducing response times and enhancing precision. My work entailed automating deployment audits and collaborating with cross-functional teams to implement scalable data solutions. My commitment to accuracy and efficiency in data management aligns with our organizational culture, and I bring a diverse perspective to our data-driven strategies, contributing to a culture of continuous improvement and innovation.
• Built and optimized data ingestion pipelines with audit balancing, ensuring data consistency and alignment between incoming files and target systems. • Automated deployment audits by developing a Python-based script to detect mismatches between edge node locations and GitLab repositories caused by manual deployments. • Conducted in-depth analysis of business-critical data, using SQL and Python to identify trends, troubleshoot inconsistencies, and deliver actionable insights. • Resolved data anomalies in large datasets by identifying root causes of inconsistencies, ensuring accuracy for downstream reporting and analytics. • Collaborated with cross-functional teams to define and implement scalable data solutions that addressed business requirements and improved operational efficiency. • Developed and automated workflows for data quality checks, reducing manual intervention and enhancing reliability across data pipelines. • Improved pipeline performance by integrating advanced error-checking mechanisms, reducing downtime and ensuring high data processing speeds. • Partnered with stakeholders to understand and address data needs, delivering tailored solutions that aligned with organizational goals. • Designed and implemented processes to ensure compliance with data governance standards, minimizing risks associated with data inaccuracies.
• Optimized data retrieval process by converting legacy Hive Query Language code hosted on the Azure cloud environment into PySpark code and reduced query response time by 73% • Performed data audit on 50K+ historical files using classification techniques such SVM and XGBoost, to generate a filtered dataset of ~1K claim cases • Designed a Python model to increase high precision matches by 89% between NICB contacts pulled from MySQL Database and existing claim contacts to detect insurance fraud
•Developed a Python Data Wrangling procedure for 10K rows of Construction Data from different sources, lowering processing time by 23% and increasing accuracy by 5% •Conducted root cause analysis to estimate the project completion date by analysing relationships and trends among variables using SQL and Python, resulting in improved precision planning by 38% •Translated analysing needs to identify cheapest source of Steel raw material into SQL queries that extracted data, and created relevant interactive Power BI Dashboards to present to stakeholders
•Evaluated results for features of the Jio Fibre broadband, and smart home solutions for JioHome, by analysing 70K+ rows of users’ networking data using SQL •Designed dashboards using Tableau by quantifying the performance metrics of the platform which improved the efficiency of the platform by 9% •Deployed Python code to develop 2 web-based data retrieval systems that conducted descriptive and multivariate statistical analysis using SQL •Supported UAT testing by identifying and resolving 120+ production issues and actively participated in 35+ critical and successful release activities