Systems for data and intelligence.

This interactive Streamlit dashboard visualizes insights from the SEER Breast Cancer Dataset (2006-2010)

This project aims to develop an accurate prediction model to guide property investment decisions in Australia. By leveraging comprehensive real estate data, the model will provide insights into market trends, regional preferences, and property valuation. The ultimate goal is to help stakeholders make informed investment choices by understanding the factors that drive property prices and demand.

This project is designed to predict trends and prices for stocks, shares, ETFs, commodities, and currency exchange rates. The goal is to provide actionable insights for investors based on data-driven predictions and analytics. The project incorporates advanced machine learning models, technical analysis, and sentiment analysis to deliver high-quality predictions and investment recommendations.

Visual Question Answering (VQA) for medical images is an advanced task in the field of medical imaging and artificial intelligence. This project aims to bridge the gap between image recognition and medical knowledge, enabling machines to comprehend and interpret the content of medical images (such as X-rays, MRIs, and CT scans) and subsequently answer questions posed in natural language based on that content. The goal is to develop a VQA system specifically designed for medical images to aid healthcare professionals in medical diagnosis and patient care.

The objective of this project is develop a predictive classifier to predict the next-day rain on the target variable RainTomorrow

This project provides a comprehensive revenue and reservation analysis for Highfield Hotel using historical data exported from booking systems and internal revenue reports. The goal is to derive actionable insights to improve room profitability, understand booking patterns, and support data-driven decision-making.

This project analyzes a dataset of telecom customers to understand factors contributing to customer churn.

This project analyzes Warren Buffett’s investment portfolio as of December 31, 2024. Using Tableau, we visualize key insights into Berkshire Hathaway’s holdings, including portfolio allocation, market value distribution, and top investments.

This project provides a dynamic pricing recommendation system using advanced machine learning and big data analytics. The system takes into account local competition, customer reviews, seasonal trends, and other relevant factors. A user-friendly GUI is included for ease of use.

This project is designed to analyze and interpret dreams using pre-trained sentiment models and NLP techniques. It helps users gain insights into their dream patterns, emotions, and themes by analyzing the textual descriptions of their dreams. Historical data is also leveraged to provide a comprehensive understanding of an individual's dream tendencies.

This repo contains analysis like a dashboard and time series forecast on NASDAQ data. Created interactive dashboards using Tableau, Power BI, or D3.js to visualize a dataset.

This project analysis a marketing campaign's success using customer data. Logistic Regression and Random Forest models were built, with the Random Forest model performing better. Feature importance identified crucial attributes, helping target campaigns. Responsiveness analysis by month revealed optimal and low-responsive periods. The 'account_balance' feature categorised customers' account balances and showed that those with 'high' balances were most responsive. The report provides actionable insights to enhance campaign effectiveness.

The goal of this project is to analyze a dataset of trending YouTube videos by leveraging a Data Lakehouse architecture using Snowflake.

This project builds an image captioning model that will analyse input images and generate a short description.

A model that recognises toxicity and minimises bias with respect to mentions of identities. If a comment made by the user is passed through this model, it will predict the toxicity of the comment.