Data Analyst Power Bi

Kirthika Kulandaivel Senthilkumar

+1-469-***-**** **********@*****.*** USA (Open to Relocation) linkedin.com/in/kirthika-k-s portfolio/kskirthika26 SUMMARY

Data Analyst with 4 years of experience in supply chain and finance analytics, skilled in SQL, Python, ETL, and CI/CD pipelines. Proven track record of delivering $1.2M+ cost savings and automating workflows to cut manual effort by 80%. Strong expertise in automation, predictive analytics, anomaly detection, and BI tools (Power BI, Tableau). SKILLS

Programming Languages/Databases: Python, R, Java, SQL (MySQL, SQL Server, MS Access, PostgreSQL, Oracle) Cloud & Data Platforms: Snowflake, AWS (S3), Microsoft Azure (Databricks), Hadoop (MapReduce, Hive), Google Cloud Platform (GCP) Data Analytics & Visualization: Power BI (DAX, Power Query), Tableau Prep, MS Excel (Pivot Tables, VBA, VLOOKUP), Looker, Alteryx Machine Learning, Libraries & Tools: Scikit-learn (Logistic Regression, Random Forest, K-Means, PCA, AUC/ROC), Pandas, NumPy, Matplotlib, Seaborn, Plotly, Streamlit, BeautifulSoup, Git, JIRA, Confluence, CRM Salesforce, ETL Pipelines, CI/CD, SDLC, Agile/Scrum PROFESSIONAL EXPERIENCE

TotalEnergies

Data Analyst Intern – Supply Chain Analytics

Houston, TX, USA

May 2024 - Present

• Recovered $1.2M by automating freight claim validation with SQL pipelines on SAP HANA reducing manual checks by 98%.

• Cut reporting time by 25% by building Power BI data models on Azure SQL and automating ETL via Azure Data Factory pipelines with T-SQL transforms and incremental loads.

• Improved refinery supply planning by building KPIs in Power BI from LP model prices, guiding buy/sell decisions for refined products.

• Defined pricing KPIs (gross margin %, discount rate) with cross-functional teams to guide discount strategies and margin control.

• Enabled AI literacy and data-driven decision making by training 30+ users on Power BI and Copilot AI, reducing ad-hoc requests by 20%

• Improved cost accuracy by 40% with a Excel VBA financial model, integrating SAP and SharePoint data for back-office month-end closing. Accenture Bank of America

Data Analyst – Credit Risk

Chennai, TN, India

Jan 2021 - Jun 2023

• Improved data accuracy in reporting workflows by identifying 15+ anomalies using SQL on credit exposure and simulation data.

• Reduced manual validation time by 40% by building Python-based ETL scripts to extract and process simulation data from AWS S3.

• Automated complex ETL workflows in Python and SQL to enable on-demand extraction, transformation, and review of credit exposure data, saving 25+ hours/month and empowering business teams with timely insights.

• Ensured accuracy across workflows by validating data mappings and outputs, reviewing 40+ JIRA tickets per sprint during QA cycles.

• Supported compliance and stakeholder decisions by presenting exposure trends using Tableau dashboards in global scrum calls.

• Ensured data integrity, stakeholder alignment, and deployment readiness by collaborating with QA and risk teams and participating in UAT reviews.

PROJECTS

Insurance Claim Prediction R, Feature Scaling, ML, Data/Business Analysis GitHub

• Built a Random Forest classifier to predict high-risk insurance claims with 92% accuracy and 0.83 AUC, applying feature engineering, data wrangling, and modeling on behavioral and demographic datasets.

• Delivered actionable business insights by segmenting customers based on claim risk, and presented results using data visualization and data storytelling in Power BI to improve fraud detection workflows. Healthcare Staffing Optimization & Analytics Python, EDA, ETL, Healthcare Analytics GitHub

• Analyzed 14K+ clinician staffing records using Python and EDA to identify underutilization trends and contractor overuse across USA.

• Delivered data-driven insights that informed nurse realignment strategies, improving resource allocation efficiency by 22% and reducing idle time and operational costs.

Instacart Product Analysis Data Visualization and Analysis Dashboard GitHub

• Queried 3M+ Instacart orders using SQL to analyze time-based purchasing behavior, basket size trends, and repeat order patterns across product categories.

• Pulled product metadata via public API and built a predictive model in Python for reorder likelihood; conducted A/B testing on bundling strategies and visualized insights in Tableau to inform retention and upsell decisions. EDUCATION

The University of Texas at Dallas Master’s, Information Technology and Management GPA 3.8 Aug 2023 - May 2025

• Relevant Courses: Data Management, Business Intelligence & Analytics with R, Statistics for Data Science, Data Visualization, Data Warehouse, Spreadsheet Modeling, Big Data, Python, Marketing, System Analysis & Product Management, Agile Project Management Anna University Bachelor’s, Electrical and Electronics Engineering GPA 3.7 Aug 2017 - May 2021

• Relevant Courses: Data Structures and Algorithms, C/C++ Programming, MATLAB, Mathematics

Contact this candidate