// Computer Engineering Student • Data Science & Machine Learning Enthusiast
I'm a Computer Engineering student from Nepal passionate about building machine learning applications and solving real-world problems with data. Over the past year, I've developed projects in customer churn prediction, recommendation systems, retail analytics, and data visualization while continuously documenting my learning through technical writing and educational content.
Hi, I'm Prajwal Subedi, a Computer Engineering student from Nepal with a strong interest in Data Science, Machine Learning, and Artificial Intelligence. I enjoy transforming raw data into meaningful insights and building practical solutions that solve real-world problems.
Over the past year, I've been developing end-to-end data science projects, including recommendation systems, customer churn prediction, retail analytics, and machine learning algorithms from scratch. Every project helps me strengthen both my technical skills and my problem-solving approach.
Beyond building projects, I believe in learning publicly and sharing knowledge. Through technical writing and my educational initiative Inflectaa, I simplify complex Data Science and AI concepts to help students and aspiring developers learn more effectively.
A growing toolkit built through hands-on projects, continuous learning, and solving real-world data science problems.
A collection of end-to-end projects demonstrating machine learning, data analysis, recommendation systems, and software development through practical applications.
Built a content-based movie recommendation system using cosine similarity and metadata feature engineering. Developed an interactive Streamlit application integrated with the TMDB API to recommend similar movies along with posters and movie information.
Analyzed telecom customer data to identify patterns behind customer churn using Python, Pandas, and Seaborn. Applied EDA and ML classification models to predict at-risk customers with high accuracy.
A series of EDA projects exploring real-world datasets — uncovering trends, distributions, and actionable insights through rich visualizations using Matplotlib and Seaborn.
Designed an end-to-end retail analytics pipeline by cleaning transactional data, performing RFM segmentation, storing processed data in SQLite, and building an interactive Streamlit dashboard for business insights.
Implemented Linear Regression and Gradient Descent from scratch using only NumPy to understand optimization, learning rate, convergence, and parameter updates without relying on machine learning libraries.
My journey of continuously learning, building real-world projects, and growing as an aspiring Data Science and Machine Learning Engineer.
Began learning Python for Data Science, SQL, statistics, and data analysis while building a strong foundation in programming and analytical thinking.
Worked on exploratory data analysis, feature engineering, machine learning algorithms, and customer churn prediction using real-world datasets.
Developed projects including a Movie Recommendation System, Retail Analytics Dashboard, and Machine Learning applications using Streamlit, FastAPI, and SQLite.
Started documenting concepts, project learnings, and practical implementation of Data Science and Machine Learning through technical writing.
Creating educational content to simplify Artificial Intelligence, Machine Learning, and Data Science concepts through videos, visual storytelling, and practical examples.
Expanding my knowledge in Machine Learning, FastAPI, recommendation systems, Power BI, and modern AI technologies while building increasingly production-ready applications.
I believe the best way to learn is by explaining concepts to others. Through technical articles, I document my learning journey, break down complex topics, and share practical insights from the projects I build.
A beginner-friendly explanation of Gradient Descent, learning rate, convergence, and Linear Regression from scratch.
Read Article →Complete walkthrough from preprocessing to deployment using Streamlit.
Read Article →Learn cosine similarity, feature engineering and content-based recommendation systems.
Read Article →Learn. Build. Share. Inspire.
Inflectaa is my educational initiative dedicated to simplifying Artificial Intelligence, Machine Learning, Data Science, and software development through practical projects, technical writing, and visual storytelling.
I'm always open to discussing new projects, data science challenges, creative collaborations, or opportunities to be part of something exciting.