Jincy George

Data Engineer, Contract

SCOTIABANK•  August 2022 - Present•  Canada

Retained to work on critical migration from Sqoop jobs to Spark, and utilized in-house PySpark-based framework to process data from diverse sources, including flat files, mainframes, and databases. Stored data in unified format to ensure compatibility across 4 business lines. Executed data migration strategies such as ingestion and conversion using big data tools such as Hadoop, Spark, YARN, and Hive, which reduced storage requirements by 15% and minimized server workload. Modified and optimized copybooks, properties, metadata, and marker files to align data with business requirements, maintained data integrity, and mitigated schema-related issues. Collaborated with downstream teams to manage project lifecycles using Agile methodologies in JIRA, and delivered post-implementation support in addressing production environment issues following source switchover.

Data Science Intern

SIRIUS COMPUTER SOLUTIONS•  January 2022 - April 2022

Collected data, performed analysis, developed models, designed dashboards, generated reports, and built analytical tools. Preprocessed data using NLP techniques such as TF-IDF, count vectorizer, tokenization, and lemmatization. Proposed data requirements to enable new use cases and generate unique insights from customer data. Applied Machine Learning algorithms such as logistic regression, naïve bayes, xgboost, and random forest. Troubleshot machine learning model issues, and made recommendations for improvements.