Freelancer profile translated to English.
Back to original languageAbout Lokman
Data Scientist | AI Expert | Machine Learning Engineer |
Computer Vision | NLP | MLOps | Python | SQL
🚀 I work on segmentation, scoring, fraud detection, image and text processing, and the ability to deploy solutions in production.
🌟Strengths :
- Dualtechnical and businessexpertise (e-commerce, finance, insurance, banking)
- Autonomy, rigor, analytical thinking,adaptability
- Ability to manage both technical development andfunctional or client follow-up
​🧰​ Tech Stack :
- ML & AI Modeling : XGBoost, LightGBM, Random Forest, logistic regression, neural networks (TensorFlow, PyTorch)
- Data Analysis & BI : Advanced SQL, Pandas, Power BI, visualization
- Computer Vision : CNN, MobileNet, ResNet, PCA, large-scale image processing
- NLP : vectorization, embeddings, text classification, semantic analysis
- MLOps & API : FastAPI, MLFlow, Evidently, deployment on Heroku / AWS
- Big Data : PySpark, AWS S3, scalable pipeline
​🌍​ Available for full remote!
French
Native or bilingual
English
Fluent
Remote only
Primarily works remotely
Experience
- 🏦 Affin Bank GroupData ScientistBANKING AND INSURANCEApril 2024 - April 2025 (1 year)Kuala Lumpur, Federal Territory of Kuala Lumpur, Malaysia• Exploratory data analysis of transactional data using SQL and Python to identify financial product usage patterns, in order to improve user experience• Contribution to the optimization of a fraud detection model by adjusting the hyperparameters of an existing model (XGBoost), improving accuracy by approximately 5% and reducing false positives by approximately 10%• Development of a dashboard on PowerBI to track KPIs related to product engagement, enabling Product and Marketing teams to evaluate weekly results
- 💵​ BanqueTraining and deployment in the Cloud of a credit scoring modelBANKING AND INSURANCEOctober 2024 - October 2024 (1 month)• Development of a credit risk prediction system with LightGBM, RandomForest, and Logistic Regression,optimized with SMOTE, under-sampling, and over-sampling, SHAP analysis to identify significant features• Deployment of a FastAPI API with Pydantic on Heroku, integration of MLflow for model monitoring anddata drift detection via Evidently, revealing data drift up to 36% on 9 out of 120 features
- 🍉 ApplicationObject recognition via a Big Data processing pipelineE-COMMERCESeptember 2024 - September 2024 (1 month)• Deployment of a scalable Big Data pipeline on AWS to process over 94,000 fruit images for a mobileapplication, using PySpark and AWS S3, real-time data processing to identify user images• Implementation of MobileNetV2 and dimensionality reduction using PCA, improving image classification quality,optimized data storage in Parquet format
Reviews
Recommendations
Be the first to recommend Lokman
Help this freelancer shine by sharing your experience working together.
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- Master of ScienceOpenClassrooms/ENSAI -2024Master en Data Science -
- Bachelor's degree in Economics & ManagementUniversity of Montpellier2016Licence en Ă©conomie & gestion