Nivedhitha Ezhilarasan

Highly skilled Data Scientist with 5 years of experience in leveraging data analytics, machine learning, and statistical modeling to drive business insights and solutions. Proficient in Python, R, SQL, and cloud technologies including AWS, Azure, and GCP. Experienced in developing and deploying machine learning models, data visualization, and end-to-end project management. Strong problem-solving abilities with a proven track record of improving business performance through data-driven strategies

Get started with Azure AI Services

KAGGLE PROJECTS

New York City Taxi Fare Prediction (August 2018 - September 2018 )

In this competition, hosted in partnership with Google Cloud and Coursera, we are tasked with predicting the fare amount (inclusive of tolls) for a taxi ride in New York City given the pickup and dropoff locations. While you can get a basic estimate based on just the distance between the two points, this will result in an RMSE of $5-$8, depending on the model used. I achieved a RMSE of 3.2 by using a deep learning model implemented in keras. Distance Calculated with Geopy in miles. Other important factors like peak hours, weekday/weekend and drop to airport were also calculated to enhance the result.

Santander Customer Transaction Prediction

In this challenge, we were to help us identify which customers will make a specific transaction in the future, irrespective of the amount of money transacted. The data provided for this competition has the same structure as the real data we have available to solve this problem. I managed to reach 80% accuracy and get top 40% in the initial phase.

https://bold.pro/my/nivedhitha-ezhilarasan

• AUTOMATED STORY ILLUSTRATION

This system is built as a part of shared task of Forum of Information Retrieval and Evaluation (FIRE) 2015 workshop. In this system we provide a methodology for automatically illustrating a given Children's story using the Wikipedia Image CLEF 2010 dataset, with appropriate images for better learning and understanding

• Unsupervised Word Embedding Based Polarity Detection for Tamil Tweets

Sentimental analysis is a sub-branch of Natural Language Processing which intends in finding out the polarity of contextual information.Tamil Tweets are collected and they are being manually tagged to develop a system that can identify the polarity. We have used word embedding and unsupervised methodology to identify the polarity of Tamil tweets. We have also evaluated our system using SAIL-2015 data set available for Tamil language and we were able to obtain state-of-the-art accuracy.