← Back to list
Registration: 27.08.2026

Caleb Djarabé

Specialization: Data Scientist
— Junior Data Scientist with a background in economics and applied mathematics (linear algebra, calculus, statistics) and hands-on experience in Python, SQL, and Machine Learning. — Experience in applied research, data analysis, predictive modeling, time series, and visualization, with clear communication of results. — Delivered Data Science projects applied to economic data, notably macroeconomic forecasting and analysis of UEMOA indicators.
Python SQL Git GitHub API rest api Excel Power BI Azure pandas Data Analysis Machine Learning FastAPI Docker MySQL CI/CD methodologies Tableau Linux Bash
— Junior Data Scientist with a background in economics and applied mathematics (linear algebra, calculus, statistics) and hands-on experience in Python, SQL, and Machine Learning. — Experience in applied research, data analysis, predictive modeling, time series, and visualization, with clear communication of results. — Delivered Data Science projects applied to economic data, notably macroeconomic forecasting and analysis of UEMOA indicators.
Python SQL Git GitHub API rest api Excel Power BI Azure pandas Data Analysis Machine Learning FastAPI Docker MySQL CI/CD methodologies Tableau Linux Bash

Portfolio

Machine Learning Project

Data Science / ML Internship Program (Elevvo Internship) — 10 tasks from Level 1 to Industry Level: regression, clustering, classification, recommendation systems, audio deep learning, time series, object detection (YOLOv8), predictive maintenance, and complete MLOps pipeline (FastAPI + Docker + CI/CD).

Prévision macroéconomique

Plateforme de prévision macroéconomique automatisée pour l'UEMOA (Afrique de l'Ouest), couvrant inflation, PIB, taux de change, masse monétaire, balance commerciale et secteurs d'activité pour plusieurs pays (Sénégal, Côte d'Ivoire, Burkina Faso, Mali). Le pipeline complet va de l'ingestion automatisée des données (via l'API DBnomics/BCEAO) à la modélisation par séries temporelles (SARIMA), avec prévisions 2026-2027 à intervalle de confiance, backtesting et analyse de corrélations entre indicateurs. Les résultats sont présentés via un dashboard interactif (React/Recharts, déployé sur Vercel) incluant export des données (CSV/JSON/PDF), page méthodologie détaillant sources et limites, comparateur multi-pays, score de vulnérabilité économique composite, et version bilingue français/anglais.

AnalystLab Internship

Data Science internship at AnalystLab Africa (remote program, 2 months), structured around concrete case studies for fictitious client scenarios. Analysis of employee attrition from the IBM HR Analytics dataset to identify the factors driving staff departures, followed by in-depth feature engineering and preprocessing work on a loan approval dataset (Loan Prediction): handling missing values, encoding categorical variables, creating new predictive variables, advanced statistical exploration and correlation analysis to prepare the data for modeling.

Skills

Python
SQL
Machine Learning
Data Analysis
Pandas
NumPy
Scikit-learn
Power BI
FastAPI
Docker
Git
GitHub
Matplotlib
Seaborn
Plotly
Streamlit
Time Series Forecasting
YOLOv8
CI/CD
Statistics
Linear Algebra
ETL
MySQL
SQLite
Jupyter Notebook
Data Cleaning
Data Visualization
K-Means
Exploratory Data Analysis
SARIMA

Work experience

Machine Learning Intern
08.2026 - 08.2026 |Elevvo Pathways
Python, Scikit-learn, YOLOv8, FastAPI, Docker, CI/CD
● Completed a hands-on internship program covering 10/10 Machine Learning tasks, from regression and clustering to industry-level applications. ● Developed classification models, recommendation systems, time series forecasting, audio classification, and object detection with YOLOv8. ● Built a predictive maintenance project and developed an MLOps pipeline (FastAPI, Docker, CI/CD) validated by 8 automated tests, all passing. ● Structured work around exploratory notebooks, reusable Python code, saved models, and results analysis.
Data Scientist Intern
08.2026 - 10.2026 |AnalystLab Africa
Python, Pandas, NumPy, Matplotlib, Seaborn, Jupyter Notebook
● Conducted exploratory data analysis on the IBM HR Analytics dataset (1,470 employees, 35 variables) to identify key factors associated with employee attrition. ● Analyzed the impact of age, monthly income, overtime, department, and job role on employee retention. ● Produced visualizations and statistical analyses using Python, Pandas, NumPy, Matplotlib, and Seaborn in Jupyter Notebook. ● Formulated initial insights to inform future predictive attrition analyses.

Educational background

Financial Engineering (Masters Degree)
since 2026 - Till the present day
WorldQuant University
Applied Economics (Bachelor’s Degree)
2020 - 2023
Université St. Charles Lwanga

Languages

FrenchNativeEnglishIntermediate