SOURAV DUBEY

CAREER SUMMARY As a recent graduate from La Trobe University, I bring a strong foundation in data engineering and a versatile skill set encompassing Python, SQL, R, Java, Scala, and ETL. My proficiency in database systems like MySQL, Oracle, and MongoDB, along with expertise in big data technologies including Hadoop, Spark, Hive, and Kafka, positions me to contribute effectively to complex data projects. I have hands-on experience designing data visualization dashboards in Tableau and optimizing data processes for efficiency. My familiarity with cloud platforms such as AWS and Azure underscores my ability to adapt and deliver scalable solutions in cloud environments.

• Turbo Stack (Python, Linear Regression):
• Engineered an automated inventory management system, Turbo Stack, combining time-series and event-based forecasting
• Utilized Python, Jupyter Notebook, and Matplotlib to implement a Linear Regression model for sales prediction
• Big Data Insights: Analyzing Bank and Twitter Data with SQL, Spark, and Docker" (SQL, Spark, Docker):
• Conducted in-depth data analysis on bank and Twitter data, uncovering valuable insights
• Applied SQL, Docker, Spark SQL, Spark RDD, and Hive to process and derive actionable information from large datasets
• Cancer Detection Algorithm (Python, PyTorch):
• Developed a sophisticated image classification model using Convolutional Neural Networks (CNN)
• Trained and fine-tuned model parameters to achieve optimal results in categorizing medical images
• Leveraged Python and PyTorch to contribute to cutting-edge advancements in cancer detection technology.

· Coursera's "Programming for everybody (getting started Python)"

· Coursera's "Mathematical Thinking in ComputerScience"