Sivanathan S. Email & Phone Number

Puducherry

Titanic Survival Analysis ProjectThis project aimed to analyze the survival outcomes of passengers aboard the Titanic, focusing on how factors like passenger class and age influenced survival rates. Leveraging SQL, Python, Tableau, and Power BI, I explored critical patterns in the data and visualized insights with interactive dashboards for a comprehensive understanding of the findings.Class Disparities in Survival: First-class passengers had nearly three times the survival rate compared to third-class passengers, highlighting significant inequities during the disaster.Age Vulnerability: Children in second class had a 100% survival rate, while those in third class faced a lower chance of survival. Seniors, particularly in second and third classes, had the lowest survival rates, with no survivors in these categories.Data-Driven Insights: Analysis revealed that age and class played crucial roles in survival chances, with patterns emphasizing the need for equitable safety protocols.Interactive Dashboards: Developed dynamic dashboards in Tableau and Power BI to present survival trends effectively and engage users with real-time data visualizations.This project provided a hands-on opportunity to apply data analytics techniques, from data cleaning and SQL queries to Python analysis and dashboard creation. It emphasized the power of combining analytics and visualization tools to uncover meaningful insights from complex datasets.The findings underscore the need for equitable safety measures and better emergency preparedness to protect vulnerable groups, including children and seniors, regardless of passenger class. This project serves as a valuable example of how data-driven decisions can inform policies to improve safety and fairness in critical situations.

Chennai, Tamil Nadu, India

The "Rumor Mill Detection" project aims to address the growing issue of misinformation by leveraging machine learning and Natural Language Processing (NLP) techniques to automatically identify and classify fake rumors. As the digital world continues to expand, distinguishing between credible and false information has become more critical. This project helps automate rumor detection, ensuring that only verified, trustworthy information circulates in digital spaces.The project begins with text data preprocessing, including tokenization, stopword removal, and stemming, to prepare the data for analysis. Various NLP techniques are used to extract important features from the text, such as sentiment, context, and linguistic patterns. These features are then passed through machine learning models, including Logistic Regression, Random Forest, and Support Vector Machines, all implemented using Scikit-Learn. Additionally, TensorFlow is used for deep learning techniques, improving the system’s ability to classify larger and more complex datasets.A significant component of the project is its accuracy in detecting fake rumors across diverse topics and sources. The system was evaluated using metrics like precision, recall, F1 score, and overall accuracy, ensuring it performs well in real-world applications. By automating the rumor detection process, the project offers a scalable solution to reduce the spread of misinformation on social media, news platforms, and other digital forums.This project is particularly beneficial for news agencies, social media platforms, and any organization dealing with information credibility. It demonstrates the power of machine learning and NLP in combating digital misinformation, ultimately promoting more reliable information-sharing practices in the digital world.

Neyveli

During my internship at NLC India Limited, Neyveli, I focused on the application of Variable Frequency Drives (VFD) in thermal power plants. The internship provided me with hands-on experience in understanding how VFD technology can be used to optimize the operation of electrical motors and improve energy efficiency. I worked closely with the plant’s control systems to study the integration of VFDs for controlling motor speeds, which plays a crucial role in reducing power consumption and enhancing the performance of plant operations. My tasks involved learning about the VFD components, analyzing operational data, and assisting in troubleshooting issues related to motor control and drive systems. I also gained valuable insights into how VFDs contribute to the overall stability and efficiency of power generation, with a focus on real-time performance monitoring and adjustments. This experience deepened my knowledge of industrial automation and reinforced my understanding of power systems, preparing me for future challenges in the energy sector.