Data Analyst with Cloud & ML Expertise

Sai Kiran Tejaswara

Data Analyst

Wisconsin 414-***-**** **********@*****.*** LinkedIn

Summary

Data Analyst with 4+ years of experience delivering analytics, ETL, BI reporting, and data-driven insights across finance, telecom, and marketing domains. Skilled in transforming raw, multi-source data into analytics-ready datasets using SQL, Python, Spark, AWS (S3, Redshift, Athena, Glue, EMR), and Azure (Databricks, Data Lake, Azure ML). Strong in building dashboards using Tableau and Power BI to track KPIs, campaign performance, sales trends, and customer behavior. Experienced in designing ETL pipelines across MySQL, PostgreSQL, MongoDB, and DynamoDB, and automating data workflows in cloud environments. Hands-on with feature engineering, PCA, clustering, and predictive modeling using scikit-learn and Spark ML. Adept at statistical analysis with R, experimentation (A/B testing), data mining, and building customer segmentation solutions. Collaborative, detail-oriented analyst with strong communication skills, delivering insights that support product, marketing, and business strategy. Education

Master's in Business Analytics Concordia University, Wisconsin Skills

Data Analytics & BI: Tableau, Power BI, Excel (Pivot Tables, VLOOKUP, Power Query), Statistical Modeling, KPI Reporting, A/B Testing, Experiment Design

Programming & Data Processing: Python (Pandas, NumPy, Matplotlib, Seaborn), PySpark, R, SQL (MySQL, PostgreSQL), Feature Engineering, Data Wrangling, EDA, Data Mining Cloud & Big Data Technologies: AWS (S3, Redshift, Athena, Glue, EMR, EC2), Azure (Azure Databricks, Azure Data Lake, Azure ML), Spark, Hadoop Ecosystem, NoSQL (MongoDB, DynamoDB) Machine Learning & Modeling: scikit-learn, Spark MLlib, Logistic Regression, Random Forest, SVM, PCA, K-Means, Gradient Boosting, Churn Prediction, Customer Segmentation ETL & Data Pipelines: ETL design, Data Integration, Query Optimization, Stored Procedures, Views, Functions, Data Quality, Automation, Pipeline Monitoring

Tools & Version Control: Git, Jupyter, VS Code, Jira, Confluence, Agile/Scrum Soft Skills: Business Storytelling, Stakeholder Communication, Requirements Gathering, Cross-Functional Collaboration, Problem Solving, Documentation

Experience

Data Analyst ACL Digital Feb 2025 - Present

• Created dashboards and interactive charts using Tableau to provide insights for managers and stakeholders and enable decision-making for market development.

• Created database objects like tables, views, procedures, and functions using SQL to provide definition, structure, and maintain data efficiently, while integrating AWS data sources such as S3, Redshift, and Athena for scalable analytics.

• Worked on designing ETL pipelines to retrieve the dataset from MySQL and MongoDB into AWS S3 bucket, managed bucket and objects access permission.

• Involved in building machine learning pipelines to do customer segmentation with Spark, clustered with PCA and K- means, and assisted the Data Scientist team to implement association rules mining.

• Ingested data, explored, cleaned and integrated data from MySQL and MongoDB databases on AWS EC2 using Python and Excel to perform initial investigation, discover patterns, and check assumptions.

• Used R to query the data, run statistical analysis and create reports and built compelling visualizations, PowerBI dashboards to deliver actionable insights, performing data cleaning and wrangling using Python

• Employed Python-based feature engineering pipelines for normalization, scaling, and categorical tokenization; implemented PCA for dimensionality reduction; and leveraged Azure ML, Azure Databricks, and Azure Data Lake to prepare and process large datasets for advanced analytics.

• Contributed in building Machine Learning models with scikit-learn library in Python, like Logistic Regression model, SVMs model, Random Forest model, and Naive Bayes model.

• Worked with cross-functional team, designed, developed and implemented a BI solution for marketing strategies along with having ability to manage multiple project tasks with changing priorities and tight deadlines in Agile environment. Data Analyst Avenir Technologies Mar 2020 - Feb 2023

• Collaborated with data managers to define and implement data standards and common data elements for data collection.

• Built ETL Pipeline using SQL to query telecom data from MySQL database by filtering, joining and aggerating various tables.

• Used Tableau to design and maintain reports and dashboards to track and communicate customer churn prediction performance.

• Manipulated the raw data with NumPy and Pandas library in Python for data cleaning, transforming and exploratory analysis and feature engineering.

• Generated interactive charts with Matplotlib and Seaborn library in Python for exploring and explaining data.

• Designed A/B tests to identify variables that contributed to customer churn and used Shiny library in R to turn analyses into dashboards.

• Applied data mining in Spark to extract diverse features that enhanced churn prediction, and integrated AWS data services (S3, Glue, EMR) with PostgreSQL and NoSQL databases such as DynamoDB to scale analytical datasets.

• Supported in constructing machine learning models using scikit-learn library in Python to predict customer churn, including Decision Tree Model, Random Forest Model, Gradient Boost Model.

• Employed Matplotlib library in Python to monitoring and analyzing Weekly/Monthly/Yearly sales data to identify market trends and patterns; developed dashboards with PowerBI to monitor business performance. Certifications

• Microsoft Certified: Power BI data Analyst Associate

• Google Data Analytics Professional Certificate-Coursera

Contact this candidate