Skip to content
View hamza-bou21's full-sized avatar

Block or report hamza-bou21

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
hamza-bou21/README.md

πŸ‘‹ Hi, I'm Hamza

Data Analyst | Analytics Engineer | Data Scientist

πŸ”— LinkedIn

GitHub followers


πŸš€ About Me

Data Analyst with a Master's in Data Science and hands-on experience building end-to-end analytics pipelines, BI dashboards, and AI-powered applications. I turn complex data into actionable business insights.

  • πŸ”­ Currently working as Business Data Analyst at byFood.com (Tokyo, Japan - Remote)
  • πŸŽ“ Master's in Data Science from University of Algiers 1
  • 🌱 Building production RAG applications + analytics pipelines
  • πŸ’Ό Open to Analytics Engineering & Data Analytics opportunities
  • 🌍 Fluent in Arabic, French, and English (C1)

πŸ“„ Resume

Download CV

Quick Highlights:

  • πŸŽ“ Master's in Data Science
  • πŸ’Ό Hands-on analytics experience across research, retail, and startup environments
  • πŸ“Š 91M+ rows processed | 99.8% data reduction

πŸ› οΈ Tech Stack

Category Technologies
Cloud & Data Warehouse BigQuery
BI & Visualization Looker Studio Power BI
Languages Python SQL
AI/ML Scikit-learn XGBoost
RAG & LLMs ChromaDB, Gemini, Groq
Tools Git Streamlit

πŸ“Œ Featured Projects

πŸš• NYC Taxi Analytics Pipeline

View Repository β†’

91M rows β†’ BigQuery β†’ Looker Studio | 99.8% data reduction | $0 query costs

  • Aggregated 91M NYC taxi trips into a 120K-row master data mart
  • Built interactive Looker Studio dashboard with 100% cross-filtering
  • Uncovered insights: Manhattan's 85% market share, cashless payment acceleration post-2020

πŸ”— Live Dashboard


πŸ›οΈ E-Commerce Analytics (Olist)

View Repository β†’

Python | Power BI | Scikit-learn | XGBoost

  • Analyzed 100K+ Brazilian orders with interactive Power BI dashboard
  • Built a predictive pipeline to forecast order delays before shipment, handling severe class imbalance (only 6.4% of orders were delayed)
  • Compared Random Forest (17% precision, minimizing false alarms) vs. XGBoost (54% recall via scale_pos_weight, catching over half of all actual delays) to evaluate the precision-recall trade-off
  • Identified freight_value, product_weight_g, and price as the strongest predictors of delivery disruption

πŸ’¬ Text-to-SQL RAG Application

View Repository β†’

BigQuery | ChromaDB | Gemini | Groq | Streamlit

  • Production RAG app enabling natural language querying of databases
  • Schema embeddings with ChromaDB, Gemini for context retrieval
  • Dual-layer security: text-level guardrails + read-only database sandbox
  • Deployed on Streamlit Cloud with live demo

πŸ”— Live Demo β†’ olist-text-to-sql-ai.streamlit.app


πŸ’Ό Work Experience

Role Company Period Type
Business Data Analyst byFood.com (Tablecross Inc.) Nov 2025 - Present Remote Contractor
Analytics Operations Assistant Smollan North Africa Sep 2025 - Nov 2025 Contract
Data Scientist Intern CERIST Research Center Dec 2024 - Jun 2025 Internship

Key achievements:

  • Automated reports with Python at byFood β†’ 70% reduction in manual reporting time
  • Built 3D lung model at CERIST β†’ 20% faster segmentation, 12% better accuracy

πŸŽ“ Education

Degree Field University Year
Master's Data Science University of Algiers 1 2025
Bachelor's Applied Mathematics University of Algiers 1 2023

🌐 Languages

Language Proficiency
Arabic Native
French Fluent
English C1 (Professional)
German Learning

πŸ“« Let's Connect


⭐️ Feel free to explore my repositories and connect with me!

Pinned Loading

  1. olist-text-to-sql-ai olist-text-to-sql-ai Public

    A secure RAG-powered Text-to-SQL interface built with Gemini 2.5 Flash, ChromaDB, and Streamlit.

    Python 1

  2. nyc-taxi-analytics-project nyc-taxi-analytics-project Public

    Analytics engineering pipeline processing 91M NYC taxi trips into a fully interactive Looker Studio dashboard. Features 99.8% data reduction and 100% cross-chart communication.

    2

  3. olist-ecommerce-analysis olist-ecommerce-analysis Public

    An end-to-end data science project on the Olist Brazilian E-Commerce dataset (99,000+ orders from 2016–2018). This project spans the entire data lifecycle

    Jupyter Notebook 2