Skip to content
View AymaneAcharki's full-sized avatar

Block or report AymaneAcharki

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.

Content in all repositories owned by your account will be closed.
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
AymaneAcharki/README.md

Aymane Acharki

Data & AI Analyst · Machine Learning · Business Intelligence

Building reliable analytics, machine learning workflows and applied AI systems around real business needs.

Current workProjectsApplied AI R&DTechnical stackFrançais

Python SQL Machine Learning Business Intelligence Azure OpenAI Ollama Hugging Face


About

I am a Data & AI Analyst, currently working as an independent Data & AI Developer and as a Genomics Data Scientist intern at DataPathology, while completing the MSc Data Analytics for Business at KEDGE Business School.

I work across the full analytical chain: translating a business need, preparing and validating data, developing models or AI workflows, and delivering outputs that people can understand and use. My background in business analysis and information technology helps me connect technical choices with operational value.

My projects cover business intelligence, machine learning, generative and agentic AI, automation and data products. Genomics and healthcare are important application areas in my current work, alongside finance, sustainability, business operations and geopolitical analysis.


Current work & selected experience

Independent Data & AI Developer · 2026–present

  • Developing Python-based Data and AI solutions for voice analysis and medical OCR.
  • Integrating local LLMs and AI agents with Ollama into existing workflows.
  • Designing privacy-aware workflows with GDPR and CNDP requirements in mind.

Genomics Data Scientist Intern · DataPathology · 2026–present

  • Contributing to the economic and legal analysis of a genomics initiative.
  • Designing a genomic data pipeline covering extraction, processing and analysis.

BNP Paribas Personal Finance × CGI · Machine Learning Hackathon · 2026

  • Built an AI-persona consumer panel simulator with a hybrid Azure OpenAI and local ML pipeline.
  • 1st-place project.

Administrative Analyst · RGA Canada · 2022–2023

  • Analyzed new-business transactions and rejection patterns through KPI dashboards.
  • Helped reduce the backlog to 5% and the rejection rate from 20% to 15%, while keeping individual errors below 1%.

Selected public projects

Project What it demonstrates Scope
EcoMeal Bot · Live demo Streamlit application combining 2,000+ recipes, environmental data, CO2 estimation, user profiles and local/cloud LLM support. Generative AI, data product, sustainability
Olympic SQL Database Seven-table SQLite model, deterministic synthetic data generation, analytical queries, integrity checks, ER diagram and data dictionary. SQL, data modeling, analytics quality
Bitcoin Market Correlations End-to-end financial-data ETL, rolling correlations, dynamic regressions and interactive Plotly visualizations. Financial analytics, time series, visualization
Global Economic & Environmental Analysis Multi-source GDP, CO2, demographic, military-spending and financial-data analysis with statistical and geospatial outputs. Business analytics, macro data, geopolitics

Applied AI R&D

PathOS

Local clinical workstation coordinating document OCR and voice-dictation workflows, with separate processing engines, human review, traceability and privacy-aware local execution.

VoxPath

Offline, CPU-compatible clinical voice workflow for pathology reporting, covering local speech processing, structured report generation and mandatory validation.

Scriptum

Offline-first medical document-intelligence engine for pathology and radiology, covering document ingestion, OCR orchestration, structured extraction, evidence traceability and human review.

These are private, active R&D projects involving proprietary components and potentially sensitive clinical workflows. They are not clinically validated medical devices or production-ready clinical systems.


Technical stack

Data, analytics & BI

Python · SQL · VBA · Excel · pandas · ETL · data cleaning · EDA · Tableau · KPI dashboards · reporting · BPMN 2.0

Machine & deep learning

scikit-learn · XGBoost · Random Forest · Classifier Chains · K-Means · PyTorch · CUDA · model evaluation · time-series analysis

Generative & agentic AI

Azure OpenAI · Azure AI Foundry · local LLMs · Ollama · AI agents · Hugging Face · Streamlit · FastAPI · human-in-the-loop workflows

Engineering & enterprise systems

Git · GitHub · Linux · pytest · Agile · data validation · offline-first systems · SAP EWM · SAP MM · SAP SD · SAP PP


Education & certification

  • MSc Data Analytics for Business, KEDGE Business School · 2024–present
  • Microsoft Azure AI-900 certification
  • Trilingual BBA, HEC Montréal · Business Analysis and Information Technology specialization
  • International experience at Universidad Católica del Uruguay and intensive C1 Spanish studies in Seville

Application domains

business operations · finance · sustainability · geopolitics · healthcare · genomics


Version française

Je suis Data & AI Analyst, actuellement développeur Data & IA indépendant et Genomics Data Scientist en stage chez DataPathology, tout en terminant le MSc Data Analytics for Business de KEDGE Business School.

Mon profil associe analyse métier et réalisation technique: compréhension du besoin, préparation et validation des données, développement de modèles ou de workflows IA, puis restitution exploitable pour la décision. Mon positionnement couvre la data analyse, la business intelligence, le machine learning, l’IA générative et agentique et l’automatisation.

La génomique et la santé sont des domaines d’application importants dans mon travail actuel, au même titre que la finance, la durabilité, les opérations métier et l’analyse géopolitique.

Expériences et réalisations

  • Développeur Data & IA indépendant: solutions Python d’analyse vocale et d’OCR médical, intégration de LLM locaux et d’agents IA avec Ollama, prise en compte du RGPD et de la CNDP.
  • DataPathology: analyse économique et juridique d’un projet génomique et conception d’un pipeline d’extraction, de traitement et d’analyse de données génomiques.
  • BNP Paribas Personal Finance × CGI: simulateur de panel consommateurs fondé sur des personas IA, combinant Azure OpenAI et modèles ML locaux; projet classé 1er.
  • RGA Canada: dashboards KPI ayant contribué à ramener le backlog à 5% et le taux de rejet de 20% à 15%, avec un taux d’erreurs individuelles inférieur à 1%.

Projets publics

Compétences principales

  • Data et BI: Python, SQL, VBA, Excel, pandas, ETL, data cleaning, EDA, Tableau, dashboards KPI, reporting et BPMN 2.0.
  • Machine learning: scikit-learn, XGBoost, Random Forest, Classifier Chains, K-Means, PyTorch et CUDA.
  • IA générative et agentique: Azure OpenAI, Azure AI Foundry, LLM locaux, Ollama, agents IA, Hugging Face, Streamlit et FastAPI.
  • Systèmes et méthodes: Git, GitHub, Linux, validation des données, systèmes offline-first et SAP EWM/MM/SD/PP.

R&D privée en IA appliquée

PathOS, VoxPath et Scriptum explorent des workflows cliniques locaux pour l’OCR documentaire, la dictée vocale, la revue humaine et la traçabilité. Ces projets privés sont des travaux de R&D actifs, pas des dispositifs médicaux validés ni des systèmes cliniques prêts pour la production.


GitHub · LinkedIn

Pinned Loading

  1. AymaneAcharki AymaneAcharki Public