Samson AMOUSSOU

As part of ESIEE’s advanced training program, I designed and delivered hands-on modules to introduce students to Artificial Intelligence and its practical applications across industry and cybersecurity. My sessions focused on bridging theoretical concepts with operational realities, encouraging both critical thinking and technical skills. Courses delivered : • AI Introduction & Applications – Covered the history, major domains (Computer Vision, NLP, Recommender Systems, Robotics), and ethical reflections. • AI & Industry 4.0 – Demonstrated how AI enhances predictive maintenance, quality control, and smart automation in industrial systems. • AI & Cybersecurity – Workshop on detecting cyber threats through AI, understanding vulnerabilities, and applying anomaly detection techniques. • Power BI Workshop – Hands-on session to explore data modeling, KPI dashboards, and interactive visual storytelling for business intelligence. Each session integrated collaborative group work, exploratory tools (e.g. LLMs, CV models), and practical case studies to simulate real-world impact. My teaching approach empowered students to design innovative AI use cases and critically assess the technologies shaping tomorrow’s world. Compétences : Intelligence Artificielle · Industrie 4.0 · Cybersécurité · Power BI · Machine Learning · Computer Vision · NLP · Analyse de données · Visualisation · ChatGPT · Formation pratique · Pédagogie active

I design and deliver data science and artificial intelligence training sessions to students with diverse backgrounds, helping them build strong technical and analytical foundations in predictive modeling, classification, clustering, and real-world AI applications. I’ve supervised hands-on projects applied to real use cases across healthcare, energy, and marketing, using advanced techniques such as SVM, Random Forest, K-means, and XGBoost. My courses cover data analysis, linear and logistic regression, statistical modeling, prediction, clustering, non-differentiable optimization, data security, and visualization. I also train students in core computer science skills, including data structures, algorithms, version control with Git, virtualization, and collaborative environments—preparing them for agile and DevOps-driven work contexts. The tools I use and teach include Python, R, SAS, SQL, TensorFlow, NumPy, Matplotlib, Scikit-learn, Tableau, Power BI, Excel, and Jupyter, always through a project-based and interactive approach.

As a Data Science, Development, and Applied Mathematics Trainer, I help students bridge the gap between theory and real-world applications. I collaborate with universities and companies to train students, from undergraduate to master’s levels, on solving real industrial problems through AI. My courses focus on applying key skills—technical, mathematical, and analytical—using tools such as Python, TensorFlow, R, and SAS. Throughout my teaching, I guide students on developing models for predictive analysis, anomaly detection, and customer segmentation. Together, we explore machine learning techniques such as logistic regression, Support Vector Machines (SVM), Random Forests, and XGBoost. I also ensure students are proficient in data preparation using SQL and data visualization through tools like Tableau and Power BI. I place a strong emphasis on practical skills. Whether it’s optimizing models for scalability or building machine learning pipelines, I design hands-on coding challenges that mimic real-world business scenarios, from sales forecasting to supply chain optimization. My goal is to equip students with the industry-relevant skills they need to excel in data science and AI.

During my time at SAE Consulting, I took on two dynamic roles: Data Analyst and Machine Learning Engineer. In these roles, I had the opportunity to work closely with clients across various industries, helping them make data-driven decisions and optimize their operations through advanced analytics and machine learning models. As a Data Analyst, I focused on extracting insights from complex datasets. I was responsible for designing and implementing data pipelines that allowed companies to visualize and interpret their data effectively. Whether it was through SQL queries, data cleaning processes, or building interactive dashboards with Tableau and Power BI, my goal was to ensure that stakeholders had access to accurate, actionable data for decision-making. Transitioning to a Machine Learning Engineer, I shifted my focus to developing and deploying machine learning models to solve specific business problems. This included designing algorithms for predictive maintenance, customer segmentation, and risk analysis. I also worked on scaling models for large datasets using tools such as Python, TensorFlow, and AWS. A key part of my role was ensuring these models were optimized for performance and integrated seamlessly into existing business processes. Throughout this experience, I learned the importance of not only building accurate models but also ensuring they align with business goals. I collaborated closely with clients to understand their needs and tailored solutions that provided tangible value. By balancing both data analytics and machine learning, I was able to help businesses transform raw data into strategic insights and drive growth.

At Inria, I was entrusted with the task of responding to the institute's data needs, particularly those related to European projects and scientific initiatives. My primary responsibility was to ensure that the management had access to accurate, timely, and actionable scientific data to support decision-making and research. To achieve this, I designed and implemented advanced data pipelines for mining data from various sources, including SQL databases, APIs, and web scrapers. I automated data retrieval processes, ensuring the smooth functioning of scripts on a weekly basis. My role also involved conducting in-depth data analysis, applying statistical methods to identify trends, patterns, and anomalies in the data. A significant highlight of my time at Inria was the creation of a data lake architecture from scratch. I defined the necessary steps, coordinated with multiple teams, and implemented the data infrastructure to centralize and organize the institute’s data assets. This included managing the allocation of tasks, setting up quality controls, and ensuring the architecture was scalable and sustainable for future use. Additionally, I conducted comparative studies and presented my findings to the research and management teams, delivering comprehensive reports and actionable insights. At the end of the project, I provided training for internal teams on how to use data visualization tools and interpret complex data sets through tailored SQL scripts and analyses. This mission culminated in the delivery of a robust, well-structured data lake and comprehensive analysis reports, positioning Inria to better harness its data for future scientific advancements.

During the ABC PAPVIRE project for the Ministry of Agriculture, I was responsible for evaluating the opportunities and challenges of introducing a new agricultural product in several West African countries. My role required close collaboration with various partners to fully understand their needs, objectives, and expectations, which helped me guide the mission effectively. I began by identifying and sourcing relevant data and developing a comprehensive mission plan. I also designed and provided training for data collection agents, equipping them with the tools and methodologies required to gather precise and reliable information on the ground. Once the data was collected, I performed advanced data matching to ensure consistency and accuracy, followed by integration and transformation of the datasets. I then created robust data flows, overseeing the transformation processes and implementing strict quality controls to guarantee the reliability of the data used in subsequent analyses. Using this data, I developed predictive models to assess market potential, and I built interactive dashboards in Tableau to visualize the results, ensuring that the insights were accessible and actionable for stakeholders from the marketing, sales, finance, and product teams. At the conclusion of this mission, I delivered a detailed report that included: - A comprehensive analysis of market opportunities and challenges. - Interactive dashboards for continuous monitoring of the market and decision-making. - Predictive model results to inform and optimize future strategic decisions. This mission helped the Ministry of Agriculture make data-driven decisions that align with market realities and capitalize on growth opportunities, thereby enhancing the project's overall impact.

At Pierre Fabre, I was entrusted with a critical mission to address data quality issues in the vinorelbine production process—an anticancer agent used in treating lung and breast cancer. The existing data was flawed and poorly processed, leading to inefficiencies in production. My objective was to correct these issues and use the data to optimize the yield of vinorelbine. After actively participating in the production workshops to understand the process, I conducted a data audit to identify error margins and systemic issues within the datasets. This comprehensive audit allowed me to pinpoint the sources of errors and reconstruct the data for internal dissemination. I developed new KPIs to enhance data analysis and decision-making, ensuring the business could better track the factors impacting production outcomes. Leveraging my expertise in SQL, I built an explainable data warehouse, designed to be used by data analysts, the method manager, and the business stakeholders. The warehouse provided clear access to clean, structured data, with appropriate monitoring tables for continuous oversight of key production metrics. In parallel, I implemented machine learning algorithms to analyze the production data, allowing us to evaluate various models and identify the most effective solutions for yield optimization. Once validated, these models were deployed in production, accompanied by automated scripts to ensure sustainability and scalability. By the end of the mission, the data warehouse was fully operational, offering seamless access to high-quality data and allowing for ongoing monitoring and optimization. The key variables that directly impacted vinorelbine yield were clearly identified, enabling the production team to focus on continuous improvement. My contributions helped improve both the efficiency and the effectiveness of vinorelbine production, providing a lasting impact on this critical area of pharmaceutical manufacturing.

At BP Conseils, I was assigned as a data analyst consultant to conduct the baseline study of indicators for the mid-term evaluation of the water and sanitation project. Initially, the necessary documents and data for this evaluation were not clearly defined. As a data analyst, I took the initiative to coordinate with the two countries involved in the study to identify the available documents and data. Then, I developed data collection tools and sent consultants to the field to gather the necessary information. After this stage, I proceeded with data preparation and visualization using Tableau. The next step involved processing the data, analyzing it, and drafting the final report. At the end of this mission, I provided a comprehensive set of performance indicators and interactive dashboards for data monitoring. I was able to improve the efficiency of the mid-term evaluation by 30% by streamlining the data collection and analysis process. I also reduced the time required to collect data by 40% through the use of well-designed data collection tools and increased the accuracy of the collected data by 25% by ensuring that field consultants used standardized methods. This allowed me to provide accurate, data-driven recommendations to improve water and sanitation management practices. Feedback from stakeholders was very positive. The visualizations in Tableau were particularly appreciated for their clarity and ease of interpretation. Decision-makers highlighted the precision and reliability of the provided data, which strengthened their confidence in the recommendations. The data-driven recommendations were integrated into the action plans.

In my role at ABDD/Plan International as a Monitoring and Evaluation Officer, I am responsible for ensuring data quality control and reporting. Nationally, I coordinate the field team (legal assistants) involved in implementing the Global Fund’s program for universal access to HIV/AIDS prevention services, community-based care, and treatment. This role includes activity planning, budget definition, quality control of legal support data, and training legal assistants on project tools. For monitoring and evaluation, I utilize tools such as Microsoft Excel for data management, Tableau and Power BI for data visualization and dashboard creation, and statistical software like SPSS or R for advanced data analysis. I also leverage project management tools like Jira for tracking project progress and collaboration, and data collection tools like KoboToolbox or ODK Collect for field data gathering. Acting as the liaison between the Global Fund partner and the legal team, I provide monthly, quarterly, semi-annual, and annual activity reports. A significant achievement in this mission was the implementation of legal data entry applications nationwide and the definition of key project indicators.