About
Data-driven professional with around 2 years of experience in .NET development and a growing specialization in
data science and AI-driven applications. Skilled in Python, SQL, and libraries such as NumPy, Pandas,
Scikit-learn, and TensorFlow with hands-on expertise in building and optimizing models for
classification, regression, and computer vision tasks.
Experienced in feature engineering, model evaluation, and deployment, with key projects including Potato
Disease Detection using CNN, Celebrity Image Classification with SVM, and Real Estate House Price
Prediction, showcasing practical applications in agriculture, computer vision, and predictive analytics.
Proficient in data visualization through interactive dashboards in Power BI, transforming complex datasets
into actionable insights for decision-making.
In addition, contributed to software solutions such as Fuel Focus, a MAUI-based app integrating Google
Maps for real-time fuel tracking and route optimization. Recognized for writing clean, efficient code,
optimizing performance, and ensuring seamless deployment of solutions across environments.
Holds a Bachelor’s degree in Electronics with a minor in Artificial Intelligence and Machine Learning,
driven by a passion for innovation in AI, automation, and business intelligence. Committed to delivering
impactful solutions that seamlessly combine data-driven intelligence with robust engineering practices.
Tools I Work with
Technical Stack
Projects
AgriVision
AgriVision is a deep learning–based solution designed to detect and classify potato leaf diseases using Convolutional Neural Networks (CNN). The system automates the process of disease identification from leaf images, enabling early detection and supporting farmers in improving crop health and yield. With a focus on accuracy and computational efficiency, AgriVision demonstrates the application of computer vision in agriculture to solve real-world challenges.
StarClass
StarClass is a machine learning project that classifies celebrity images using Support Vector Machines (SVM). The solution emphasizes effective feature extraction and engineering to handle variations in facial features, lighting, and pose. By combining feature engineering with a robust classifier, the system achieves reliable accuracy in distinguishing between multiple celebrity classes. This project highlights expertise in computer vision, classical ML algorithms, and preprocessing techniques for real-world image datasets.
PriceProphet
PriceProphet is a machine learning–based regression model designed to predict real estate house prices using historical housing data. The project involves data preprocessing, feature engineering, and exploratory data analysis (EDA) to identify key factors influencing property value, such as location, size, and amenities. By applying regression techniques and evaluating performance with metrics like RMSE and R², PriceProphet delivers accurate and data-driven price estimates, showcasing skills in predictive modeling and applied machine learning.
