Profile picture
RASHAMVIR KAUR GRANG
Professional Summary

B.E. Computer Science graduate specialising in Big Data Analytics with hands-on experience in Python, SQL, and Power BI. Published researcher with two peer-reviewed papers and expertise in data analysis, visualisation, and business intelligence.

Skills
Programming Languages — Python, SQL
Analytics Concepts — EDA, Data Cleaning, Statistical Analysis, Feature Engineering, ETL, Dashboard Design
Databases & Tools — MySQL, Jupyter Notebook, Streamlit, Git/GitHub
BI and Visualization — Power BI, Excel, Google Looker Studio
Libraries — Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn
Education

B.E. Computer Science Engineering (Big Data Analytics)

Chandigarh University
2022 – 2026 | Mohali, India

CGPA: 7.89

POSITIONS OF RESPONSIBILITY

Class Representative

Chandigarh University
  • •Represented the student body by coordinating communication between students and faculty, strengthening leadership, teamwork, and problem-solving skills.

    • Co-Lead / Event Coordinator

    HackMinds Club, Chandigarh University
  • •Co-led CU's UK Education Fair in collaboration with IEEE Student Branch and FATEH Education, coordinating logistics, registrations, and stakeholder communication.
    • Projects
  • •Built a supply chain risk scoring engine in Python across 800 orders and 8 global suppliers, flagging a 43% delay rate using composite signals, delay history, port weather risk, and freight index.
  • •Developed 90-day per-product demand forecasts with scikit-learn and EOQ-based reorder alerts, deployed as a live Streamlit dashboard with a What-If delay simulator.
  • •Analysed 7,000+ telecom customers using SQL and Python, identifying month-to-month contracts (43% churn) and new customers under 12 months (48% churn) as the highest-risk segments.
  • •Quantified $139K monthly revenue at risk from churn and visualised retention opportunities by contract type, tenure, and payment method in a Google Looker Studio dashboard.
  • •Analysed 99K+ real-world Brazilian e-commerce orders (Olist dataset) across 2 years, surfacing a 20x revenue growth trend from Oct 2016 to Aug 2018 and peak AOV patterns by month.
  • •Built a 6-month revenue forecast using Linear Regression and visualised monthly KPIs, category performance, and trend in an interactive Power BI dashboard.
    • Research Papers

    Credit Card Fraud Detection⁠⁠

    Published in IEEE Xplore Proceedings
  • •Trained and compared 5 models on imbalanced transaction data using SMOTE; XGBoost and Random Forest outperformed Decision Tree and Isolation Forest on Precision and Recall for fraud class detection.
  • •Published in IEEE Xplore documenting end-to-end pipeline, preprocessing, SMOTE resampling, feature scaling, and cross-model evaluation on AUC-ROC, F1, and Confusion Matrix.

    • Graph-RAG for Legal Contract Analysis⁠

    Computer Science Journal (Scopus-indexed)
  • •Built a Graph-RAG pipeline using Neo4j, FAISS vector search, LangChain, and Gemini LLM to enable multi-hop reasoning and explainable clause retrieval across legal contracts.
  • •Benchmarked against Vector-RAG on the CUAD dataset (510 contracts), achieving Precision@5 of 0.76 and Recall@5 of 0.88, demonstrating measurable improvement in retrieval accuracy.
    • Certifications
    Languages
    English|Hindi|Punjabi
    Interests
    Traveling|Baking|Sketching