Portrait of Sana Ur Rehman Arain

DATA SCIENTIST · ANALYTICS ENGINEER · BI SPECIALIST

Sana Ur Rehman Arain

I turn raw data into decisions — 10+ years across banking, fintech, and logistics, specializing in credit risk analytics, machine learning, and business intelligence. Currently exploring the intersection of ML and quantitative finance.

View Projects Download Résumé Open to opportunities
0 Years of
Experience
0 Route Efficiency
Gain — UPS
0 Operational
Cost Reduction
0 Faster Data
Retrieval

01 — About

Professional Summary

Data Analyst and Data Scientist with 10+ years of experience in financial services and logistics. I specialize in credit risk analytics, machine learning, business intelligence, and data-driven process optimization — with advanced proficiency in Python, SQL, R, Power BI, Tableau, and cloud platforms (AWS, Azure, GCP).

My toolkit spans TensorFlow, Keras, and Scikit-learn for modeling; Apache Airflow and BigQuery for ETL; and Looker for interactive reporting. I'm currently based in Braga, Portugal, and exploring the intersection of AI and quantitative finance in my own research projects.

02 — Experience

Where I've Worked

Data Analyst / Reporting Officer (Freelance)

United Bank Limited

Nov 2025 — Present Banking
  • Analyze and consolidate data from multiple systems to support performance tracking, MIS reporting, and incentive calculations.
  • Calculate and manage multiple incentive schemes and dashboards.
  • Coordinate with managers, HR, and IT for accurate processing.
  • Generate analytical and operational reports, ensuring compliance and supporting audits.

Risk / Data Analyst

Revolut

Apr 2024 — Oct 2025 Fintech
  • Analyzed large-scale credit card and loan datasets using SQL and Python.
  • Built Looker and Tableau dashboards to track KPIs.
  • Developed machine learning credit scoring models to reduce default risk.
  • Delivered training on credit risk and data literacy.

Independent Data Analyst & Analytics Engineer (Freelance)

Self-Employed

Jan 2020 — Dec 2024 Cloud & ETL
  • Architected cloud-native data platforms on GCP.
  • Designed ETL pipelines using Python and Apache Airflow.
  • Designed and implemented CI/CD pipelines to automate testing and deployment of Python-based ETL workflows and predictive models.
  • Built BI solutions using Looker and Looker Studio.
  • Migrated on-premise systems to AWS, Azure, and Snowflake.
  • Developed predictive models and executive dashboards.

Data Analyst

UPS, Sweden

Jan 2020 — Feb 2024 Logistics
  • Developed ML clustering models improving route efficiency by 20%.
  • Reduced annual expenses by 15% using SQL cost analysis.
  • Built Power BI and Looker dashboards.
  • Integrated data into GCP for BI reporting.

03 — Skills

Tech Stack & Tools

Programming & ML

PythonSQLR PandasNumPyScikit-learn TensorFlowKerasSpark Hadoop

Visualization & BI

Power BITableauExcel LookerLooker Studio

Databases

MySQLPostgreSQLIBM Db2 SnowflakeBigQuery

Cloud

AWSMicrosoft AzureGoogle Cloud

Tools & MLOps

GitGitHub Actions / CI-CDApache Airflow JIRAConfluence

Domains

Credit RiskFinancial AnalysisDeep Learning ForecastingA/B TestingData Warehousing Supply Chain Optimization

04 — Projects

Every project links to its repository. Deep Learning, Quantitative Finance, and Financial Engineering projects are actively in progress — track them in the full index.

Data Science

sustainability-ai-smart-cities

Multi-modal AI using satellite imagery and financial data to predict Urban Heat Islands.

View on GitHub ↗
SQL

FaceRecog-DB-Core-SQL

High-performance attendance database simulating 100,000+ records — composite indexes cut lookup time by 99%.

View on GitHub ↗
SQL

Bank-Vault-Core-SQL

ACID-compliant banking database with stored procedures for safe transfers and automated fraud-detection triggers.

View on GitHub ↗
SQL

E_Commerce_SQL

Relational database for online shopping — inventory triggers, ACID transactions, and CLV analytics.

View on GitHub ↗
SQL

Retail-Sales-Analytics-SQL

End-to-end pipeline: Python extraction, MySQL analysis, and Matplotlib/Seaborn visual insights.

View on GitHub ↗
SQL

hotel-management-system-sql

Relational database for hotels with dynamic pricing engines and overlap-safe availability logic.

View on GitHub ↗
R

human_development_index_R

Predicting HDI with automated ETL (World Bank API), PCA/Preston Curve EDA, and model comparison.

View on GitHub ↗
R

student-performance-analysis-R

Statistical inference on academic performance drivers using multivariate regression, ANOVA, and t-tests.

View on GitHub ↗
R

Customer_Churn_Analysis_R

Telecom churn prediction with R & Tidymodels (AUC 0.86) — full EDA and retention strategy.

View on GitHub ↗
R

life-expectancy-analysis-R

Global life expectancy drivers — Tidyverse cleaning, ggplot2 visuals, Caret predictive modeling.

View on GitHub ↗
Linux

End-to-End-Data-Science-Pipeline

Automated pipeline on Ubuntu: CLI exploration, Pandas ETL, MySQL modeling, SQL analytics via Makefiles.

View on GitHub ↗
In Progress

+ Deep Learning, Quant Finance & Financial Engineering

Deep hedging, rough volatility, neural SDEs, GAN market simulation, and more — see the live index.

Browse the full index ↗

05 — Education

Academic Background

🎓

MSc, Financial Engineering

WorldQuant University

🎓

MBA, Business Analytics

O.P. Jindal Global University

🎓

BS, Computer Science

University of the People

🎓

Bachelor of Business Administration

University of the People

🎓

Bachelor of Commerce

University of Sindh

06 — Certifications

Licenses & Certifications

🏅Google Advanced Data Analytics
🏅Google Data Analytics
🏅Google IT Support
🏅IBM Data Science
🏅IBM Data Analyst
🏅IBM Data Engineering
🏅IBM Cybersecurity Analyst
🏅IBM IT Scrum Master
🏅Johns Hopkins Data Science Specialization
🏅Business Intelligence Analyst Specialization (Tableau)
🏅Microsoft Power BI Data Analyst

07 — Contact

Let's talk data.

Open to data science, analytics engineering, and BI roles — and always glad to talk quant finance, dashboards, or your next data pipeline.

Braga, Portugal · © Sana Ur Rehman Arain