Ankur Rana - Data Analyst

About

Results-driven Data Analyst with experience in leveraging advanced SQL, Python, and machine learning to transform complex datasets into actionable insights. Expert in developing predictive models, optimizing ETL pipelines, and crafting interactive dashboards with Tableau and Power BI, consistently improving data accuracy, reducing processing times, and enhancing strategic decision-making.

Work Experience

Data Analyst

Epics, ASU

Aug 2024 - Jun 2025

Tempe, Arizona, US

Led the development and deployment of predictive models and advanced analytics solutions for financial risk assessment, optimizing data accuracy and informing strategic decisions.

Developed and deployed predictive models for financial risk assessment using scikit-learn, regression, and classification algorithms, improving risk prediction accuracy by 35%.
Executed comprehensive exploratory data analysis (EDA) and feature engineering on large-scale financial datasets with Python, SQL, and R, identifying key risk factors and trends to inform strategic decision-making.
Boosted data accuracy by 65% and relevance by 42% by integrating five external financial data sources and implementing real-time KPI dashboards with SAS.
Processed and integrated over 1TB of structured and unstructured financial data using Azure Blob Storage and Azure Synapse Analytics, optimizing ETL pipelines and advanced analytics workflows.
Designed and implemented interactive Power BI dashboards for financial trends, credit risk, and fraud detection, reducing manual analysis time by over 15 hours per month and enabling business leaders to make informed financial decisions.

Data Analyst

CIEK Solutions

Oct 2023 - May 2024

Tempe, Arizona, US

Revamped data reporting systems and optimized data processing pipelines, significantly enhancing report accuracy and operational efficiency for stakeholders.

Revamped a scorecard reporting system by integrating real-time upstream data pipelines, increasing report accuracy by 20% and accelerating stakeholder decision-making.
Engineered a scalable data ingestion pipeline using Python (Pandas, NumPy) and SQL, automating data cleaning and transformation, improving data integrity by 25% and reducing manual intervention by 40%.
Developed and optimized complex DAX expressions in Power BI, enabling real-time KPI tracking and enhancing user insights by 30% through interactive dashboards.
Redesigned data models and indexing strategies in SQL Server, reducing dashboard load time by 50% and improving overall system responsiveness.
Automated job scheduling and query performance tuning with ETL frameworks and SQL stored procedures, cutting data processing time by 40% and ensuring seamless data refresh cycles.

Education

Information Technology

Arizona State University

9

Aug 2022 - May 2024

Tempe, Arizona, US

Computer Science

SRM Institute of Science and Technology

8.56

Jul 2018 - May 2022

Chennai, Tamil Nadu, IN

Projects

Customer Churn Prediction

Jan 2024 - Dec 2024

Developed and deployed an end-to-end churn prediction pipeline using data cleaning, EDA, feature engineering, and a Random Forest model (85% accuracy), integrated with a Flask API for real-time predictions. Delivered business impact by reducing churn by 10% in the pilot phase and enabling stakeholders to track insights through dynamic Tableau dashboards.

Languages

English

Skills

Databases

MySQL
MS SQL
MongoDB
Snowflake
SparkSQL
Oracle

Data Analysis / ETL Tools

Power BI
Tableau
Data Bricks
MS Excel
Google Analytics
Data Modeling
Data Mapping
Data Mining
Data Extraction
Data Transformation
Salesforce
Zendesk
Confluence
Postman
Query Optimization
ETL

Frameworks & Tools

NumPy
Pandas
Matplotlib
Statistics
Agile
Hadoop
Hive
PySpark
Seaborn
Sci-kit Learn
JIRA
KPI Analysis
Automation Power Query
SSIS
SSRS
SAS
Informatica Power Center
Regression
Sklearn
SciPy
Hypothesis Testing
Neural Prophet

Cloud & DevOps

AWS (Amazon Web Services)
Microsoft Azure
Jenkins
Git
CI/CD
Snowflake

Programming Languages

Python
R
SQL
NoSQL