Skip to content
View SimonNC's full-sized avatar
2 followers · 7 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Highlights

  • Pro

Block or report SimonNC

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
SimonNC/README.md

👋 Simon Jorite | Data Analyst

Certified Microsoft Power BI Data Analyst (PL-300) with experience in data-driven finance, operations, and e-commerce environments. I design reliable analytics pipelines and decision-ready KPIs, enabling business and executive teams to act on consistent, trustworthy data.

🎯 Professional Positioning

I specialize in transforming complex, fragmented datasets into clear, actionable KPIs and storytelling dashboards. My approach is rooted in analytical rigor and scalability, ensuring every insight is backed by a reliable "Single Source of Truth."

  • Problem Solver: I identify operational bottlenecks, such as delivery delay impacts on customer satisfaction.
  • Business-Oriented: Experience in data-driven finance, operations, and e-commerce environments, translating technical metrics into strategic recommendations.
  • Engineering Mindset: I treat data as a product, implementing multi-layered architectures (staging → marts) and CI/CD workflows to ensure data quality.

🛠️ Technical Stack

  • Data Transformation: SQL (PostgreSQL, DuckDB), dbt (Data Build Tool), Python (Pandas, NumPy).
  • Business Intelligence: Power BI (Expert DAX, Star-Schema Modeling, Power Query), Automated Reporting.
  • Analytics Engineering: Data Modeling (Fact/Dimension), Data Quality Testing, Version Control (Git/GitHub), GitHub Actions (CI).
  • Machine Learning: Scikit-learn (Logistic Regression, Random Forest), Feature Engineering, Model Evaluation (ROC-AUC, Recall), Leakage-safe pipelines.
  • Methodology: Exploratory Data Analysis (EDA), KPI Design, Retention Analysis, Customer Lifetime Value (CLV).

🚀 Featured Data Projects

1. Olist E-commerce: End-to-End BI Solution

  • Business Problem: Quantify the impact of logistics performance on customer satisfaction to reduce negative reviews.
  • Approach: Built a full pipeline from raw CSVs to interactive dashboards. Conducted deep EDA with Python to identify the "25-30 day delivery" threshold where satisfaction collapses.
  • Tech: Python for cleaning/EDA, Parquet for performance, and Power BI for executive storytelling using a Star-Schema model.
  • Impact: Identified that deliveries exceeding 30 days generate 64% of negative reviews. Recommended proactive alerts at the 20-day mark and region-specific SLA adjustments.

2. Analytics Engineering with dbt & DuckDB

  • Business Problem: Fragmented raw data led to inconsistent KPI reporting. The goal was to build a modern, SQL-centric data warehouse architecture.
  • Approach: Implemented a layered dbt project (staging, intermediate, marts) using DuckDB. Focused on mastering data grains and separating technical IDs from business entities.
  • Tech & Quality: SQL-only transformations, dbt Core, Data Contracts (dbt tests), and GitHub Actions for automated CI/CD and documentation.
  • Impact: Delivered "BI-Ready" marts for Revenue and Retention. Established a Single Source of Truth where data quality is enforced by automated tests, reducing manual audit time.

3. Telco Customer Churn Prediction – ML Decision Support

  • Business Problem: Customer churn represents a major financial risk in the telecom industry, where customer acquisition is significantly more expensive than retention. The objective was to proactively identify high-risk customers in order to support data-driven retention strategies.
  • Approach: Conducted business-oriented EDA to identify key churn drivers (contract type, tenure, support & security services). Built a leakage-safe ML pipeline with a recall-first strategy, comparing an interpretable Logistic Regression baseline with a Random Forest model. Deployed the final model into a Streamlit decision-support application allowing customer profile simulation and threshold tuning.
  • Tech: Python (Pandas, NumPy, Scikit-learn), Random Forest, Logistic Regression, joblib, Streamlit, Git/GitHub.
  • Impact: Improved churn detection with a Random Forest model reaching 0.84 ROC-AUC and 0.73 recall on churners. Delivered an actionable tool enabling business teams to identify at-risk customers early and simulate retention strategies based on real-time churn probabilities.

📜 Certifications

  • Microsoft Certified: Power BI Data Analyst Associate (PL-300)
  • Data Analytics Bootcamp: Le Wagon (RNCP Level 6 / Bachelor's equivalent)
  • AWS Certified: Solutions Architect – Associate (In Progress)

📫 Contact & Opportunities

Pinned Loading

  1. olist-data-analysis olist-data-analysis Public

    End-to-End Data Analytics Project: Transforming Data into Business Insights with Python & Power BI

    Jupyter Notebook

  2. olist-dbt-duckdb olist-dbt-duckdb Public

    SQL-only analytics project using dbt + DuckDB on the Olist e-commerce dataset

    Python

  3. telco-customer-churn-prediction telco-customer-churn-prediction Public

    End-to-end data science project on customer churn prediction, from business understanding and EDA to modeling and deployment with Streamlit.

    Jupyter Notebook