Aspiring Technologist & Computer Scientist

• Developed a Self-Organizing Map (SOM) in Python using MiniSOM to analyze daily behavioral data, including wake-up times, sleep hours, and activities. Preprocessed and normalized data with Pandas and NumPy , and encoded categorical features with LabelEncoder to prepare for unsupervised learning. Learned to map multidimensional personal data into a 2D space for cluster analysis and visualization.
• Implemented visualization techniques with Matplotlib , including heatmaps and scatter plots , to display cluster densities and highlight trends in daily patterns. Converted numerical results back to human-readable formats to interpret wake-up times, sleep durations, and activity trends effectively. Gained hands-on experience in turning raw dataset insights into clear, actionable visualizations. 

• Built a flexible prediction system using the trained SOM to estimate missing values based on the closest clusters. Learned to normalize and denormalize inputs , handle categorical encoding, and compute cluster-based averages for predictions. Strengthened practical skills in neural network-based unsupervised learning, predictive modeling, and end-to-end machine learning workflows.