Abhinandan Samal

• Engineered efficient queries to extract and process complex data, enabling real-time analysis across 50+ KSQL streams. • Developed an automated solution for handling and rerouting deserialized Kafka records from error logs, enhancing system reliability. • Collaborated closely with Senior Architects to refine project architecture, and successfully deployed data processing pipelines via Azure DevOps.

• Developed statistical and predictive data models to recommend offers on a dataset of 13 million records, resulting in a 15% increase in cross-selling and a 9% increase in up-selling for the bank. • Initiated and implemented machine learning pipelines for various use cases, including Customer Churn Prediction in the banking sector. • Conducted activities such as data collection, data model discussions, data cleaning, and exploratory data analysis on complex, imbalanced, and large datasets.

Organized large datasets using advanced querying, visualization, and analytics tools, improving data accessibility and actionable insights. Developed new components for custom ETL modules, enabling 4 new use-cases for customer recommendation, and significantly expanding product capabilities. Engineered proof-of-concepts with PySpark to streamline data processing, optimizing both batch and real-time data handling.

Resolved client queries, executed data jobs, and generated daily and monthly reports, ensuring timely completion of dashboards.