AI · DATA SCIENCE · MACHINE LEARNING · UX

Projects

A selection of applied Artificial Intelligence, Machine Learning, Data Science, Computer Vision, Natural Language Processing, and model deployment projects. These projects document my progression from data analysis and classical machine learning to neural networks, generative AI, and production-oriented model deployment.

Explore Projects ↓

Portfolio

Applied AI Projects

The portfolio demonstrates a progressive learning journey across data analytics, machine learning, deep learning, computer vision, generative AI, API development, and production deployment.

JUL 2026

Model Deployment

SuperKart

SuperKart is a retail forecasting project focused on predicting quarterly sales revenue across supermarkets and food marts located in different city tiers. The predictive solution supports inventory optimization and regional sales strategy while demonstrating how a machine-learning model can be operationalized and deployed at scale.

Skills & Technologies

EDA · Data Preprocessing · Model Building · Hyperparameter Tuning · Docker · Flask · REST API · Streamlit · Hugging Face

Key Learnings

This project strengthened my understanding of the complete machine-learning deployment lifecycle. I gained practical experience moving from exploratory analysis and model optimization to API development, containerization, application development, and cloud-oriented deployment. It also demonstrated the importance of designing models not only for predictive performance, but also for accessibility, reproducibility, and real-world operational use.

JUL 2026

Introduction to Computer Vision

HelmNet

HelmNet is a computer-vision project designed to automatically determine whether workers are wearing safety helmets. The objective is to support workplace safety, increase monitoring efficiency, and reduce the human error associated with manual safety compliance inspections.

Skills & Technologies

Exploratory Data Analysis · Image Preprocessing · Convolutional Neural Networks · Transfer Learning · Fine-Tuning · Data Augmentation

Key Learnings

Through HelmNet, I developed practical experience with image classification and deep-learning workflows. I learned how data augmentation, transfer learning, and fine-tuning can improve model generalization, particularly when working with limited image datasets. The project also reinforced the importance of evaluating AI systems in the context of their real-world safety implications.

JUL 2026

Natural Language Processing with Generative AI

Medical Assistant

The Medical Assistant project explores a Retrieval-Augmented Generation architecture designed to retrieve relevant information from established medical manuals and provide context-aware responses. The project examines how generative AI can support information retrieval, structured decision support, and consistent access to medical knowledge.

Skills & Technologies

Retrieval-Augmented Generation (RAG) · Large Language Models · Prompt Engineering · Data Preprocessing

Key Learnings

This project expanded my understanding of generative-AI architectures and the role of external knowledge sources in improving LLM responses. I gained experience with document preparation, retrieval pipelines, prompt design, and grounding model responses in source material. I also explored the importance of reliability, traceability, and responsible design when AI systems operate within healthcare-related contexts.

MAY 2026

Introduction to Neural Networks

ReneWind

ReneWind focuses on predicting wind-turbine generator failures using sensor data. The objective is to support proactive maintenance, reduce repair costs, and minimize unplanned downtime by identifying potential equipment failures before breakdowns occur.

Skills & Technologies

EDA · Data Preprocessing · Classification · Activation Functions · Neural Networks

Key Learnings

ReneWind provided practical experience in constructing neural-network classification models and understanding the effect of architecture and activation functions on predictive performance. A particularly important learning was the need to align model evaluation with business consequences, especially where false negatives can result in costly equipment failures.

MAY 2026

Advanced Machine Learning

EasyVisa

EasyVisa applies advanced machine-learning techniques to historical visa application data in order to identify factors associated with certification outcomes. The project compares ensemble approaches and develops predictive models that can support evidence-based analysis of application profiles.

Skills & Technologies

EDA · Data Preprocessing · Bagging · Boosting · Stacking · Hyperparameter Tuning · Business Insights

Key Learnings

This project deepened my knowledge of ensemble machine-learning methods and model optimization. I gained experience comparing bagging, boosting, and stacking approaches, tuning model parameters, interpreting feature importance, and translating model outputs into meaningful analytical insights.

MAR 2026

Machine Learning

Personal Loan Campaign

This project analyzes customer attributes to identify individuals with a high likelihood of accepting a personal-loan offer. A predictive model is developed to support more effective customer targeting and improve the efficiency of marketing campaigns.

Skills & Technologies

EDA · Data Preprocessing · Decision Trees · Model Evaluation · Model Improvement · Business Recommendations

Key Learnings

The project strengthened my understanding of supervised machine learning and decision-tree models. I gained experience evaluating classification performance, identifying important customer characteristics, improving model performance, and connecting analytical findings with practical marketing recommendations.

MAR 2026

Python Foundations

FoodHub

FoodHub is an exploratory data-analysis project examining customer orders, restaurant demand, cuisine preferences, ratings, and delivery patterns for a food-aggregation platform. The objective is to transform transactional data into actionable insights that can improve customer experience and business decisions.

Skills & Technologies

Python · NumPy · Pandas · Seaborn · Exploratory Data Analysis · Univariate Analysis · Bivariate Analysis · Business Recommendations

Key Learnings

This project strengthened my Python programming skills and provided practical experience with data manipulation, exploratory data analysis, and statistical examination of datasets. I developed competencies in univariate and bivariate analysis, text-oriented analysis, interpretation of customer sentiment, and creation of informative visualizations for communicating analytical findings.

Learning Journey

From Data Analysis to Deployed AI

Together, these projects represent a progression from Python-based exploratory analysis and classical machine learning toward ensemble methods, neural networks, computer vision, retrieval-augmented generation, and production-ready AI deployment. The portfolio reflects both technical development and an increasing focus on building AI systems that address practical user and organizational needs.

Capabilities Demonstrated

Data Science

Python
Pandas & NumPy
Exploratory Data Analysis
Data Visualization
Feature Engineering

Machine Learning

Classification
Decision Trees
Ensemble Models
Hyperparameter Tuning
Model Evaluation

Deep Learning & AI

Neural Networks
Computer Vision
CNNs
Transfer Learning
RAG & LLMs

Deployment

Flask
REST APIs
Docker
Streamlit
Hugging Face

Research, AI & User-Centered Technology

My broader interest lies at the intersection of Artificial Intelligence, User Experience, Usability, and applied software development. These projects serve both as technical experiments and as a foundation for investigating how intelligent systems can deliver useful, usable, and meaningful experiences.