Best LLM Fine-Tunning Project
Fake MTN’s bot 
Posts by Collection
certificates
Doctoral Training School Foundational Methods in Data Science
Certificate of attendance
IEEE Volunteering
In recognition of the creation of the IEEE Cameroon Data Science, AI and IoT Group 
MLOps ZOOMCAMP Certificate
MLOps Training 
cv
projects
Firewall CPU consumption prediction
This study presents a framework for monitoring and predicting CPU usage of a virtualized firewall deployed in a software-defined networking (SDN) environment within a Campus Area Network (CAN).
MLOps for deploying of a fraud detection model
This project was developed as part of the MLOps Zoomcamp certification and delivers a microservice for mobile money operators across Africa to identify and block fraudulent transactions in real time. certificate
Water detection leakage
The objective of this academic work is to develop an artificial intelligence model capable of detecting leaks within a water distribution operator’s network using historical data collected from water meters.
Face Emotion Recognition
This academic work presents a series of experiments aimed at improving the performance of an artificial intelligence model dedicated to facial expression recognition. The primary objective is to optimize the detection of basic facial emotions from image data. The experiments are conducted using the Face Emotion Recognition (FER-2013) dataset.
Thrips detection (Cap2020)
Study conducted as part of AI4Industry 2026, focusing on the analysis of the impact of controlled noise on improving the detection of insects known as thrips.
research
Fraud detection using Kolmogorov-Arnold Network (KAN)
In this study, we explored the Kolmogorov–Arnold Network for financial fraud detection. This approach was chosen for its interpretability, in contrast to traditional neural networks.
Fraud detection using Kolmogorov-Arnold Network (KAN)-XGboost
This study builds on the work of Gislain, Zeutouo & Yurievich, Kostyuchenko. (2025). Fraud detection using Kolmogorov-Arnold Network. and aimed to improve the performance of the initial fraud detection model for Mobile Money transactions, which is based on the KAN algorithm paper. More specifically, it seeks to optimize data preprocessing to enhance model convergence and to reduce false negatives and false positives by combining the KAN model with the XGBoost algorithm.
Recommended citation: Nolack Tapsir Gislain Zeutouo, Evgeniy Yurievich Kostyuchenko, and Serge Ndoumin (2025). "An Ensemble KAN-XGBoost Model for Fraud Detection."
Download Paper
summer_school
Summer School and Workshop in Data Science
Published:
Participated in a summer school and hands-on workshop covering core concepts in data science. Completed an introductory course in R programming and acquired foundational knowledge in MLOps, including model deployment principles, workflow automation, and best practices for managing machine learning systems in production.
Doctoral Training School – Foundational Methods in Data Science
Published:
Participated in an intensive doctoral training program focused on foundational methods in Data Science. As part of the practical component, fine-tuned the large language model LLaMA to develop a domain-specific conversational system capable of responding to user queries related to the services offered by MTN Rwanda, combining NLP techniques with real-world telecom use cases.
teaching
Lecturer: Virtualization and Cloud Computing
Graduate course, Institut Saint Jean accrédité CTI Et Label EUR-ACE, 2022
From September 2022 to April 2025, I taught courses covering virtualization concepts, including the creation and management of virtual machines using VirtualBox, as well as containerization of Python applications with Docker and their deployment using AWS simulators (LocalStack).
Lecturer: Big Data, Webscraping and Webmining
Graduate course, Institut Sous-Régional de Statistique et d'Économie Appliquée (ISSEA), 2024
From December 2024 to March 2025, I taught and supervised practical sessions on big data processing using PySpark, web data extraction with BeautifulSoup, Selenium, and Scrapy, and the application of Natural Language Processing (NLP) techniques for text cleaning, analysis, and information extraction