A highly motivated individual with a keen interest in exploring the vast realm of data science. Possessing a solid foundation in the computer world, I am driven by creativity and a commitment to delivering optimal results in every project. Eager to apply my knowledge and skills, I am actively seeking opportunities to contribute to the field of data science, gain valuable experience, and further develop my personal and professional capabilities.
I had the privilege of working alongside seasoned data scientists, learning the ropes of data manipulation, predictive modeling, and data-driven decision-making. The realworld projects I was involved in equipped me with practical skills and insights that extend beyond the classroom. My time at Orange not only deepened my understanding of the role data plays in the telecom industry but also solidified my passion for data science. I'm grateful for the mentorship and hands-on experience I gained during my training, and I am eager to apply these skills to contribute meaningfully in the field of data science moving forward.
Python
Data analysis
Data preprocessing
Data Visualization
Statistical Analysis
Machine Learning
Neural Networks
Power Bi
Problem solving
Communication skills
Time Management
Orange Academy project
The dataset focuses on customers using Orange's fiber optics service, providing detailed information on demographics, usage patterns, and a key target variable indicating whether a customer has discontinued the service. The primary challenge addressed by the dataset is customer churn, which is the rate at which customers terminate their relationship with Orange. Despite a low churn rate of 0.5%, the dataset is crucial for identifying at-risk customers and implementing targeted retention strategies to maintain a strong customer base. This dataset is valuable for gaining insights to enhance customer retention for Orange's fiber optic service.
University Graduation Project
AI-powered Traffic Sign Detection and Classification Models
The project aimed to address the lack of understanding of traffic signs using AI.
Two architectures, CNN and YOLOv5, were utilized for traffic sign detection and classification.
The CNN model achieved 98% accuracy on a local dataset, while YOLOv5 achieved 95% accuracy with robust detection capabilities.
The project demonstrated the potential of AI in enhancing road safety and driving assistance systems.