The project explores the efficient management of material flow at Indian Oil Corporation Limited’s refinery, focusing on the processes of procurement, tendering, transportation, and inventory management. It examines the structured roles within the Material and Contracts Department, highlighting each stage from purchase requisition to material arrival and inspection. Emphasis is placed on the perpetual inventory system, the use of SAP software, and the ABC analysis method for inventory categorization. The study also discusses the importance of quality control during material reception, proper record-keeping, and the structured approach to storing and handling materials to support smooth plant operations.
Fashion ReVibe breathes new life into TrendTide’s fast fashion brand by blending sustainability, inclusivity, and digital-first strategies tailored for Gen Z and Millennials. Anchored in data-driven insights, the campaign includes influencer-driven Instagram Reels, community-driven “StyleSwap” pop-ups, an AI-powered style quiz, and limited-edition drops—all designed to re-engage a youth-driven audience. By addressing key consumer demands—sustainable materials (30%), inclusive sizing (25%), and authentic, interactive content—the project aims to increase Instagram engagement to 4%, reduce churn to 35%, and boost online sales by ₹1–1.4 crore, revitalizing TrendTide’s brand for a more ethical and vibrant future.
This project explores forecasting and analyzing price trends for DOGE-USD and Ethereum USD using time series data spanning nearly five years (2019–2024). By applying descriptive statistics and ARIMA models in RStudio, the project investigates volatility, distribution shapes, and patterns within the cryptocurrency data. The analysis reveals DOGE-USD's high volatility with mean-reverting tendencies, modeled using ARIMA(0,0,1). Ethereum USD, with more moderate fluctuations, is best represented by an ARIMA(1,0,1) model capturing momentum effects. Despite reasonable short-term stability predictions, uncertainty remains due to inherent market fluctuations, highlighting the need for cautious interpretation of these forecasts.
This project analyzes the readmission patterns of diabetic patients at HealthFirst Multispeciality Hospital. Using a dataset from the UC Irvine Machine Learning Repository, it leverages data cleaning, Principal Component Analysis (PCA), Random Forest, K-Means clustering, and logistic regression to predict readmission risk. While Random Forest achieved moderate accuracy (48.25%), logistic regression underperformed due to data imbalance. Key insights revealed that treatment complexity, hospitalization history, age-related risks, and emergency visits significantly influence readmission. Actionable strategies include optimizing medication regimens, enhancing telehealth monitoring, and leveraging data analytics to proactively identify high-risk patients, improving patient care and hospital efficiency.
0
0
Delete Project
This action cannot be undone
Are you sure you want to delete ""? This will permanently remove the project and all its associated data.
