PROJECTS Data Lake Foundation and Forecasting. Client – PostNord, Sweden
Developed and optimised Azure Data Factory pipelines to load data from onpremise and cloud source systems. Implemented batch processing via Full load and Incremental load.
Loaded streaming data from Kafka topics to Data Lake via Azure Databricks using PySpark and Python, into various staging layers.
Enabled various forecasting and prediction models. Enabled various Power BI reports and Dashboards by transforming the data. SQL performance tuning in SQL Server Management Studio for low latency and high throughput. Data Ingestion Framework. Client – QBE Insurance, North America
Integrated and transformed data in different file formats like json, csv, avro, parquet etc using Databricks, Data Factory and PySpark.
Data Ingestion from on-premise and cloud data sources, and facilitate data governance and streamlining operations of Azure Data Engineering resources. Modern Warehousing and Analytics. Client – Select Equity Group, United States of America Data Mapping of business systems data in Azure cloud environment to support the needs and objectives of the organizational units and vendors.
Worked with Offshore Delivery team and Organization's leadership to drive Digital Transformations initiatives with Cloud Computing, Data Engineering and Analytics. Predictor System | Recommender System| Classifier Model – Personal Projects
Performed Data Cleansing, Exploratory Data Analysis, Text Pre-processing, Model Building, Model Evaluation, Model Improvement and Website Deployment.
Car Price Predictor | Cricket Win Probability Predictor | Email/SMS Spam Classifier | Book Recommender System | Movie Recommender System