Data Analyst Power Bi

Siri Penumatsa Data Analyst

****@***********.*** 947-***-**** Northville, MI Linkedin GitHub

PROFILE

Data analyst with 4+ years of experience in business intelligence, statistical analysis, and automated forecasting. Proven track record of leveraging SQL, Tableau, and Power BI to drive operational improvements and support data-driven decision making. Strong background in developing automated forecasting models and delivering actionable business insights to stakeholders. Experienced in requirements gathering, metric definition, and influencing business decisions through quantitative analysis.

SKILLS

Business Intelligence: Tableau, Power BI, SQL, Excel (Advanced), Data Modeling

Analysis & Forecasting: Statistical Analysis, Regression Modeling, Predictive Analytics

Data Processing: ETL, Data Warehousing, Python, R

Business Tools: Jira, Microsoft Project, AWS

Core Competencies: Data Pipeline Architecture, Data Security, Process Automation, Cross-functional Collaboration

PROFESSIONAL EXPERIENCE

Data Analyst, LightEdge Solutions 06/2023 – present Remote, USA

Developed automated forecasting models using statistical methodologies, resulting in 25% improvement in prediction accuracy for resource planning

Created comprehensive Power BI dashboards with advanced DAX expressions to track operational KPIs, enabling data-driven decision making across departments

Designed and implemented ETL workflows to integrate data from multiple sources, ensuring accurate and timely reporting for business stakeholders

Performed in-depth analysis of operational metrics using SQL and Python, identifying cost optimization opportunities and process inefficiencies

Collaborated with business teams to define requirements and establish metrics for measuring operational performance

Authored detailed technical documentation and presented findings to influence stakeholder decisions

Programmer Analyst, Cognizant Technology Solutions 01/2020 – 07/2022 Hyderabad, India

Built and maintained automated data pipelines using SQL Server and Hadoop to process large-scale operational data

Designed interactive QlikView dashboards for operational metrics, improving stakeholder visibility into key business processes

Conducted statistical analysis and regression modeling to identify trends and optimize business processes

Implemented cloud-based solutions for scalable data processing and reporting

Collaborated with business teams to gather requirements and translate them into technical specifications

Machine Learning Intern, Inventrom Private Limited 05/2019 – 12/2019 Hyderabad, India

Developed predictive models using Python and SQL to forecast business metrics

Created Tableau dashboards to visualize performance metrics and model results

Assisted in requirements gathering and documentation for analytics projects

ACADEMIC PROJECTS

Power BI Sales Insights Project 06/2024

Tools Used: Python, MySQL, Apache Airflow, AWS Redshift

Implementation: Architected end-to-end data pipeline for sales data integration. Developed automated ETL workflows using Apache Airflow for data extraction and transformation. Implemented data warehousing solution using AWS Redshift.

Results: Processed 100GB+ of daily sales data with 99.9% accuracy, reducing data processing time by 45% and enabling real-time sales analytics.

Customer Churn Prediction Model for E-commerce Platform 06/2024

Tools Used: Python, PostgreSQL, Apache Spark, AWS EMR, Amazon S3

Implementation: Designed and implemented end-to-end ETL pipelines to process customer transaction data. Built scalable data infrastructure using AWS EMR for large-scale data processing. Created automated data quality validation frameworks using Python and SQL.

Result: Successfully processed 50GB+ of customer data daily with 99.9% accuracy, enabling real-time churn predictions and reducing processing time by 40%.

Deaths caused byAir Pollution 03/2024

Tools Used: Apache Kafka, Amazon S3, AWS Glue, Python, SQL

Implementation: Architected real-time data ingestion pipeline using Apache Kafka for streaming pollution data. Developed ETL workflows with AWS Glue for data transformation and integration. Implemented data quality checks and monitoring systems.

Result: Built a scalable data pipeline processing 1M+ records daily, enabling real-time pollution monitoring with sub-second latency.

E-Waste Classification Using Deep Learning 11/2023

Tools Used: Python, AWS S3, AWS Glue, PostgreSQL

Implementation: Designed data infrastructure for processing and storing large-scale image datasets. Created ETL pipelines for efficient data preprocessing and feature extraction. Implemented automated data validation and quality control processes.

Result: Successfully processed and managed 2TB+ of image data while maintaining data integrity and accessibility for model training.

EDUCATION

Central Michigan University, Masters of Science 08/2022 – 05/2024 Mount Pleasant, MI Computer Science

Geethanjali College of Engineering and Technology,

Bachelors of Technology

08/2017 – 07/2021 Hyderabad, India

CERTIFICATES

Google Data Analytics Professional Certificate

Contact this candidate