Siva V Email and Phone Number

Executed advanced SQL queries and PySpark operations to manipulate and analyze data, resulting in an efficiencyimprovement of approximately 40%, optimizing performance and facilitating actionable insights. Deployed machine learning models (Linear Regression, Decision Trees, Random Forest) to forecast shipping and distributiondemand, reducing forecasting errors by up to 30% and enhancing operational planning and resources. Collaborated with cross-functional teams, including… Show more Executed advanced SQL queries and PySpark operations to manipulate and analyze data, resulting in an efficiencyimprovement of approximately 40%, optimizing performance and facilitating actionable insights. Deployed machine learning models (Linear Regression, Decision Trees, Random Forest) to forecast shipping and distributiondemand, reducing forecasting errors by up to 30% and enhancing operational planning and resources. Collaborated with cross-functional teams, including data analysts, scientists, and business teams, to craft bespoke datasolutions, resulting in a substantial around 25% boost in operational efficiency. Built interactive Power BI dashboards and reports for visualizing shipping and distribution data, streamlining decisionmaking processes and enhancing strategic insights, resulting in around a 45% reduction in decision time. Designed and implemented scalable ETL processes, integrating data from over 12 diverse sources into the company's datawarehouse using Apache Kafka for real-time data streaming and Py Spark for distributed processing. Utilized Microsoft Azure services (Blob Storage, Azure SQL Database, Azure Functions) for seamless data Show less

Designed and implemented ETL pipelines using Python, SQL, Apache Kafka, and Apache Airflow, integrating 8 datasources into AWS cloud services to enhance shipping and distribution demand forecasting accuracy. Utilized Databricks Unified Analytics Platform to harness the power of Apache Spark for scalable and efficient dataprocessing within ETL workflows, enhancing overall pipeline performance and throughput. Employed Python libraries such as pandas and NumPy within Databricks… Show more Designed and implemented ETL pipelines using Python, SQL, Apache Kafka, and Apache Airflow, integrating 8 datasources into AWS cloud services to enhance shipping and distribution demand forecasting accuracy. Utilized Databricks Unified Analytics Platform to harness the power of Apache Spark for scalable and efficient dataprocessing within ETL workflows, enhancing overall pipeline performance and throughput. Employed Python libraries such as pandas and NumPy within Databricks notebooks for streamlined data manipulation andanalysis, optimizing data processing speed and efficiency across the ETL lifecycle. Implemented Apache Airflow workflows to orchestrate complex data transformations and scheduling tasks, achieving 20%faster processing times for predictive modeling and analysis on AWS S3 and Amazon RDS. Collaborated closely with data scientists to develop and validate demand forecasting models, utilizing advanced statisticalanalysis, machine learning algorithms, and Spark-based computations within Databricks, leading to a 15% enhancement insupply chain logistics optimization and forecast accuracy. Maintained operational dashboards using Amazon QuickSight in Databricks, enabling stakeholders to make informeddecisions and improving operational efficiency and customer satisfaction. Managed critical infrastructure components, including Apache Kafka clusters, AWS Glue, and Databricks clusters, to enablereal-time data processing and scalable analytics aligned with business requirements. Ensured high data integrity, security, and compliance in Databricks environment with monitoring, maintenance, anddocumentation, bolstering trust in analytics-driven decision processes and achieving a 9.0 data integrity rating Show less