About

Hello! I’m Prabhu Subramanian. I am a passionate Data Analyst and Machine Learning enthusiast. I analyze data meticulously to bring out its various potentials in building a predictive model, producing an efficient way to explain data through EDA and visualizations. I’m an expert in Python (PEP8), SQL, and Tableau.

I offer excellent analytical and communication skills. My strive is to learn, teach and enhance my skills as an avid Data Analyst, Cloud Practitioner, and Machine Learning enthusiast with a parallel knowledge of Data Engineering.

Basic Information
Address:
San Francisco, U.S.A
Languages:
English, Hindi, Tamil, Malayalam
Professional Skills
Programming languages: Python, SQL, HTML, CSS, Java, JavaScript

Database: MySQL, Microsoft SQL Server, PostgreSQL, Oracle, Snowflake, Arora, Redshift, DynamoDB, Teradata

Cloud Engineering: Google Cloud Platform, Amazon Web Services, Microsoft Azure, Databricks

Business Integration: Tableau, Microsoft Power BI, Excel, SAP, BI HANA

Data Visualization: matplotlib, seaborn, ggplot2, Plotly

Version Control: Git, GitHub, Bitbucket, SVN Tortoise

Python
90%
SQL
90%
JavaScript
60%
HTML
80%
CSS
75%
C/C#
50%
Work Experience

April 2021 - Present

Levi Strauss & Co.
Data Analyst

  • Provided guidance as a Subject Matter Expert (SME) for critical reports, and aligning with business objectives for over 500 users.
  • Automated and enhanced various reports, ensuring 100% end-to-end automation without any manual intervention. Incorporated intricate logic to dynamically generate reports for daily/weekly/monthly/yearly reporting requirements.
  • Innovatively designed and executed multiple Proof of Concepts (POCs) using Python, Alteryx, and ETL techniques, enhancing operational efficiency.
  • Utilized PySpark on Databricks to automate reporting solutions and visualize data on PowerBI for business users.
  • Developed an API to bridge the gap between Alteryx and SharePoint, enabling comprehensive reporting analysis and saving approximately 15 hours of manual data transfer per week.
  • Mentored peers and facilitated training sessions to enhance reporting capabilities and streamline data integration processes.

January 2019 - December 2020

Squark AI
Graduate Programmer Analyst

  • Enhanced model accuracy by an impressive 70% through the application of advanced NLP techniques such as word2vec & BERT, resulting in more precise predictions and decision-making processes.
  • Developed production code integrating the MinIO framework with AWS S3, significantly streamlining data storage and retrieval processes, leading to a 50% reduction in data access time.
  • Formalized subprocesses to execute the JVM H2O engine, effectively optimizing computational performance and resource utilization, resulting in a 40% increase in processing speed.
  • Developed and devised a multiprocessing and multithreading solution to enhance efficiency further.
  • Implemented an automation script using Python and CLI, dramatically reducing developers' testing time by an outstanding 90%, thereby accelerating the development cycle and time-to-market.
  • Established testing logs and a web interface through Grafana dashboard integration, enhancing visibility and monitoring capabilities.
  • Thoroughly documented all development pipelines on Confluence, ensuring clear communication and knowledge sharing within the team.

January 2020 - June 2020

Peterbilt Motor Company (PACCAR)
Data Engineer Intern

  • Implemented scripts to preprocess and optimize the speed by an impressive 50% for cleaning customer warranty data using Python & SQL, resulting in a significant reduction in data processing time and operational costs.
  • Enhanced NLP model accuracy by introducing spelling dictionaries and incorporating manufacturing plant failure modes word corpus.
  • Administered data warehouse pipelines from various sources including Snowflake, Teradata, and Excel, deploying CI/CD pipelines using Jenkins and CloudFormation.
  • Established a logging and notification pipeline for internal team communication using AWS services.
  • Deployed pipeline using Docker, Kubernetes (EKS), and AWS Services - SNS, SQS, SES, S3, EC2, Lambda.

November 2015 - July 2018

Hewlett Packard
Software Engineer

  • Designed and implemented Enterprise Resource Planning (ERP) dashboards catering to Supply Chain, Manufacturing, and Finance departments, resulting in a 20% increase in supply chain visibility, a 15% reduction in manufacturing downtime, and a 25% improvement in financial forecasting accuracy.
  • Achieved a remarkable 68% improvement in application query optimization, leading to a 30% reduction in report generation time and a 25% increase in overall system performance, resulting in significant cost savings and enhanced productivity.
  • Improved Customer Self-Service operations by 30%, leading to a 25% rise in satisfaction ratings and a 20% drop-in ticket resolution time, showcasing leadership in operational excellence and customer focus.
  • Customized and deployed a Kanban process utilizing SQL functions and triggers, streamlining workflow management.

Education

2018 - 2020

Master's Degree
M.S. in Information Systems

Northeastern University

Relevant Coursework: Data Management & Database Design, Designing Data Architecture & Business Intelligence, Big Data Architecture & Governance, Project Planning & Management

2011 - 2015

Bachelor's Degree
B.S in Electronics & Telecommunication

University of Pune

Relevant Coursework: Signal Processing, Communication Systems, Digital Signal Processing, Wireless Communication, Embedded Systems, Internet of Things (IoT), Mobile Communication

References
My Tableau Public Dashboard
Contact Me
Let's connect:

Address

San Francisco, U.S.A

Email

prabhus165@gmail.com

Developed by Prabhu Subramanian

Built with:

Copyright © Prabhu Subramanian 2024 All rights Reserved

MIT LICENSE LICENSE MIT LICENSE