Project Details

In this project, I developed a comprehensive sales report using Excel Pivot Tables to help businesses analyze customer discount strategies, support effective negotiations, and identify potential expansion opportunities in high-performing regions. The report delivers actionable insights and data-driven recommendations to optimize sales performance, improve customer satisfaction, and increase overall revenue.

During this project, I gained hands-on experience in the following areas:

1. Pivot Tables
2. Power Query
3. DAX (Fundamentals)
4. Conditional Formatting
5. Report Design and Visualization
6.Sales Domain Metrics

Overall, this project focuses on enabling businesses to efficiently track, assess, and improve their sales operations. By leveraging data analysis techniques, organizations can uncover growth opportunities, make informed decisions, and maintain a competitive edge in a dynamic market environment.

Project Details

The objective of this project was to develop a unified report that can be effectively used by stakeholders across sales, marketing, finance, and executive teams. The report focuses on building a strong data foundation, designing user-centric visuals, and enabling interactive, drill-down insights for better analysis and decision-making.

Key areas of focus included:

1. Robust data modeling
2. User-focused report design
3. Interactive and drillable insights

Throughout this project, I gained experience in:

1. Power Query (basic and advanced transformations)
2. Writing both simple and complex DAX formulas
3. Data modeling with more than 10 interconnected tables
4. Selecting appropriate visuals and applying effective formatting
5. Dashboard design best practices
6. Utilizing bookmarks for navigation
7. Publishing reports on Power BI Service
8. Incorporating stakeholder feedback
9. Understanding key metric

Live Interactive Dashboard

Project Details

The Hotel Revenue Insight Dashboard is an interactive Power BI solution designed to analyze and monitor key performance metrics in the hospitality sector. It provides a comprehensive view of KPIs such as Revenue, ADR (Average Daily Rate), RevPAR (Revenue per Available Room), Occupancy Rate, and Realisation % to evaluate overall business performance.

The dashboard enables stakeholders to track week-on-week trends, compare performance across cities and properties, and identify revenue-driving factors through dynamic filters and drill-down capabilities. It also highlights revenue distribution by category (Luxury vs Business), booking platform performance, and property-level insights for deeper analysis.

Advanced data modeling with multiple tables, along with optimized DAX measures and Power Query transformations, ensures accurate and efficient reporting. The user-friendly design and interactive visuals make it easier for decision-makers to uncover patterns.

Project Details

The Fake News Detection System is a Machine Learning and Natural Language Processing (NLP) project designed to classify news articles as real or fake. The project focuses on combating misinformation by analyzing textual data and identifying patterns that distinguish authentic news from misleading content.

The system begins with data preprocessing, including text cleaning and tokenization, followed by feature extraction using NLP techniques to convert textual data into meaningful numerical representations. Multiple supervised learning algorithms are then trained on labeled datasets to build an accurate prediction model.

The model is evaluated using performance metrics to ensure reliability and effectiveness in real-world scenarios. Visualization tools are used to analyze results and improve model performance.

This solution can be used in social media monitoring, news moderation, and research to help users make informed decisions and limit the spread of misinformation.

Project Details

Developed an AI-powered system for detecting and classifying brain tumors from MRI images using deep learning and transfer learning (VGG16). The model accurately classifies images into Glioma, Meningioma, Pituitary Tumor, and No Tumor, achieving around 95% testing accuracy with strong overall performance. The project includes data preprocessing, image augmentation, model training, and evaluation using metrics such as confusion matrix and ROC curve. A robust architecture was designed by fine-tuning the VGG16 model with additional dense and dropout layers to enhance performance and reduce overfitting. The system is deployed as a Flask-based web application, enabling users to upload MRI images and receive real-time predictions along with confidence scores. Built using Python, TensorFlow, Keras, and Scikit-learn, the solution provides an efficient, accurate, and user-friendly approach for automated medical image analysis.