Trinath Vandavasi Guru

Master’s student in Data Science at Tagliatela College of Engineering, University of New Haven, with a strong foundation in Machine Learning, Data Analysis, and SQL. Holds a Computer Science degree with hands-on experience in data-driven problem-solving, statistical modelling, and database management. Proficient in Python, SQL, and data visualization, passionate about leveraging machine learning for business insights. Core competencies: Data Science & Machine Learning: Statistical Analysis Predictive Modeling Big Data Analytics PowerBI Programming & Tools: Python SQL C R AWS PowerShell Research & Analysis: Architectures Data Science Pipelines

• Drug Recommendation system using Machine Learning Models, 06/23 - 09/23, This project focuses on classifying patients' medical conditions by analyzing their reviews. The dataset underwent preprocessing, including the removal of stop words, text normalization, and the exclusion of the date feature, as it was determined to be irrelevant for model development. To transform the textual review data into numerical features, we employed the TF-IDF vectorizer. Several machine learning models were then trained and evaluated, including Logistic Regression, Random Forest, Support Vector Machine (SVM), Gradient Boosting, Decision Tree. Additionally, the project generated recommendations for the top 5 most popular drugs based on patient ratings. However, it is important to note that drug effectiveness can vary among individuals, and these recommendations should be interpreted as general guidelines rather than personalized medical advice.
• Natural Language Processing for Sentiment Analysis with Deep Learning, 11/23 - 03/24, In order to identify and analyze the thoughts, feelings, and sentiments indicated in textual data, the field of sentiment analysis is crucial. Deep learning models have become effective tools for sentiment analysis thanks to their capacity to recognize semantic links and understand complicated patterns. We investigate different deep learning architectures, such as recurrent neural networks (RNNs), convolutional neural networks (CNNs), and transformer-based models, to assess how well they are able to capture nuances in sentiment and contextual information. The results of this study open the door for more advanced applications in this field by giving important new insights into the capabilities and constraints of deep learning models for sentiment analysis.