Professional Profile

I am a Data Scientist and Statistical Engineer with a strong background in statistics, probability, optimization, and econometrics.

I develop machine learning solutions for predictive modeling—including job seeker risk assessment, churn analysis, NLP, high-dimensional data analysis, and predictive maintenance (RUL). I also conduct surveys and statistical analyses for diverse applications, and I have completed projects involving model deployment (MLOps) and cloud-based integrations with AWS.

Technologies: Python, SQL, scikit-learn, TensorFlow, Keras, PyTorch, Spark, AWS, Docker, FastAPI, Flask, Streamlit, R, SAS, Shiny, Power BI.

Projects

Here are some of my projects in machine learning, cloud, and data analytics.

Happiness Scores – Linear Mixed Models

Analysis of World Happiness Report data (2015–2023) using linear mixed models to estimate fixed effects (GDP, life expectancy, etc.) and random effects (country‑specific intercepts and trends).

GitHub Repo View Analysis
Tools: R, lme4, lmerTest, ggplot2, tidyverse, Quarto, GitHub Pages

YOLOv5 Object Detection API

REST API built with FastAPI and YOLOv5 for image object detection, packaged in Docker with automated testing and Swagger UI.

GitHub Repo Docker Hub
Tools: Python, FastAPI, YOLOv5, Docker, Pytest, Uvicorn

Remaining Useful Life Prediction

End‑to‑end predictive‑maintenance solution for turbofan engines: ingest and preprocess NASA CMAPSS FD001 data, engineer time‑series features, train a LightGBM model for Remaining Useful Life (RUL) prediction, and deliver interactive monitoring & diagnostics (error distribution, life‑stage gauge, SHAP explainability) via Streamlit.

GitHub Repo Live Demo
Tools: Python, Pandas, scikit‑learn, LightGBM, Optuna, SHAP, Streamlit, Altair

World Happiness Dashboard

Interactive Shiny dashboard using World Happiness Report data (2015–2023), with global trend analysis, country profiles, and predictive modeling.

GitHub Repo Live Demo
Tools: R, Shiny, ggplot2, leaflet, plotly, FactoMineR

Machine Learning Exercises on AWS

Hands‑on implementations of AWS AI services : Rekognition for image labeling, Textract for document parsing, Comprehend for sentiment analysis, Transcribe & Translate for audio, and Lex for conversational bots.

GitHub Repo
Tools: Python, AWS CLI, Boto3, Rekognition, Textract, Comprehend, Transcribe, Translate, Lex

Filmalyze

Streamlit dashboard for movie discovery, processing a 10 000‑film Kaggle dataset to explore by genre, year, rating and revenue, generate personalized recommendations, and visualize rating & box‑office trends.

GitHub Repo
Tools: matplotlib, seaborn, pandas, numpy, plotly, streamlit

Looking for more? Explore additional projects on my GitHub.

My Background

Education

Master’s Degree – Statistics for Evaluation and Forecasting

Sep 2024 – Sep 2026

University of Reims Champagne-Ardenne, France

Engineer – Statistics and Decision Science

2018 – 2022

National School of Statistics and Economic Analysis, Senegal

Languages

  • French – Native
  • English – B2
  • Wolof – Native

Certifications

  • AWS Cloud Practitioner Essentials – AWS (2025)
  • Introduction to Machine Learning on AWS – AWS (2025)
  • Machine Learning in Production – DeepLearning.AI (2025)
  • SAS Certified Specialist: Base Programming Using SAS 9.4 – SAS (2025)

Professional Experience

Statistical Analyst

ANSD, Senegal (Aug 2022 – Jul 2024)
  • Led projects on enterprise data and business surveys: CUCI update survey, RNEA data cleansing and reconciliation, NINEAWEB migration.
  • Analyzed business demographics and supported national accounts rebasing.
  • Processed data requests for business registers (CUCI, RNEA, RGE).

Tools: Python, R, Stata, Excel, QGIS, Survey Solutions

Data Scientist Intern

ANSD, Senegal (Mar 2022 – Jul 2022)
  • Developed predictive models for long-term unemployment risk.
  • Created an interactive Shiny web app for risk profiling and visualization.

Tools: R, Shiny, Stata, Excel

Data Analyst Intern

ANSD, Senegal (Sep 2021 – Nov 2021)
  • Analyzed socio-demographic factors affecting contraceptive use among young women.
  • Proposed solutions to improve access to contraceptive services.

Tools: R, Stata, Excel

Field Data Specialist

ENSAE, Senegal (Aug 2021 – Oct 2021)
  • Designed ODK survey tools and trained field staff for the national survey on COVID-19 impacts on businesses and households.
  • Supervised the fieldwork for this survey.

Tools: ODK, XLSForm

Let’s Connect

Interested in working together or discussing a project? Feel free to reach out.

Email LinkedIn GitHub