Likhita Yakanuru

Analytical and detail-oriented aspiring Data Analyst with a strong foundation in data interpretation and trend analysis. Skilled in designing data processing systems and utilizing advanced analytics tools to extract insights from complex datasets. Passionate about leveraging data-driven approaches to optimize decision-making in tech-centric environments.

• Intro to NoSQL
• Create a Data Project with Neo4j
• Learning Ubuntu Desktop
• Introduction to Linux
• Apache Kafka Essential Training
• MLOps Essentials: Model Development and Integration

• Fine-tuned BERT for Rating Predictions: A Sentiment Analysis Study on Amazon, Conducted sentiment analysis on Amazon reviews using a fine-tuned BERT-base-cased model., Leveraged transfer learning to train the model for predicting ratings from textual content., Used Mean Squared Error (MSE) as the evaluation metric., Performed performance assessment, attention mechanism analysis, and error analysis., Optimized model complexity for real-time applications while balancing performance and interpretability.
• Software Fault Prediction Based on Feature Selection Algorithm, Evaluated seven distinct machine learning algorithms using datasets from public PROMISE repositories., Focused on improving software quality by identifying and addressing defects efficiently., Assisted users in selecting the most effective algorithm for specific tasks., Enhanced software engineering outcomes through data-driven decision-making.
• Adverse Drug Reaction (ADR) Analysis, Analyzed ADR patterns using FDA's FAERS data to identify high-risk drugs and patient groups., Applied logistic regression, survival analysis, and machine learning models., Conducted EDA, statistical testing, and data preprocessing to improve drug safety insights., Identified key patterns in ADR occurrences, improving drug safety assessments.