Jyothsna Kaamala

Data Analyst

Extracted, cleaned, and managed large-scale pharmacovigilance datasets using SQL, Python, and AWS for efficient data processing. Developed machine learning models and statistical analyses to predict and identify adverse drug reactions, achieving significant accuracy improvements. Created interactive dashboards in Tableau for real-time ADR monitoring,reducing reporting delays by 15%. Collaborated with cross-functional teams to enable proactive risk management and improve regulatory compliance, saving costs and enhancing safety outcomes.

Data Analyst

Developed financial forecasting models and applied advanced statistical techniques to analyze customer behavior, achieving a variance under 5% and increasing retention rates by 8%. Implemented AWS data solutions and optimized SQL databases, improving data retrieval efficiency by 35% and enhancing overall performance. Engineered and maintained Power BI dashboards for real-time financial monitoring, enabling strategic decision-making and actionable insights. Spearheaded data mapping, transformation, and risk assessment initiatives, ensuring accurate reporting, regulatory compliance, and effective financial risk mitigation.

M. S, Data Science

B. Tech, Electronics and Communication Engineering

Visualizing Institutional Rankings using Tableau

This project aims to create an interactive dashboard for analyzing university rankings using various key metrics. The dashboard leverages data visualization techniques to help prospective students and their families make informed decisions about higher education institutions. The visualizations include university admission rates, SAT scores, financial information, student demographics, and other relevant data points.

Tech Stack: Tableau, Excel, CSV, Data Visualization, Data Analysis, Data Storytelling

GitHub

Movie Rating Prediction using IMDB Datasets

This project involves building a machine learning model to predict a movie’s average rating using publicly available IMDB datasets. By leveraging data such as genres, runtime, and other movie characteristics, we aim to gain insights into the factors influencing movie ratings and provide a predictive tool. The model can be useful for film producers, streaming platforms, and movie enthusiasts to understand the dynamics of movie ratings and predict a movie’s success in terms of audience reception.

Tech Stack: Python, Jupyter Notebook, Pandas, NumPy, Matplotlib, Scikit-Learn, Machine Learning, Data Preprocessing, Feature Engineering, Data Visualization, Model Evaluation, Hyperparameter Tuning.

GitHub

Real-Time Data Processing and Analytics Using Kafka, Docker, Python, and OpenSearch

This project implements a real-time data processing and analytics system using modern technologies such as Apache Kafka, Docker, Python, and OpenSearch. The system is designed to ingest, process, store, and visualize streaming data in real time. It is ideal for scenarios such as monitoring application logs, tracking user activities, or analyzing sensor data, enabling actionable insights from continuous data streams.

Tech Stack: Apache Kafka, Docker, Python, OpenSearch, JSON, Data Streaming, Data Processing, Data Analytics, Data Visualization, Real-Time Data, Data Ingestion, Data Storage.

GitHub

Cafe Delight Website using AWS Cloud Services

The Cafe Delight Website is an online platform designed to showcase a café's offerings, provide an intuitive user interface for customers to explore menus, and facilitate seamless online reservations and orders. The website will be powered by AWS Cloud Services, ensuring scalability, reliability, and performance. This project leverages modern web development practices and AWS’s robust cloud infrastructure to deliver an optimized user experience for café patrons and administrators.

Tech Stack: JSON, AWS Lambda, Amazon RDS, Amazon DynamoDB, Amazon S3, Amazon EC2, AWS QuickSight, AWS Elastic Beanstalk.

Predict Future Sales using R

This project focuses on predicting future sales using a dataset from a Kaggle competition. The dataset includes historical sales data from a Russian software company, and the goal is to forecast total sales for every product and store in the next month.

Tech Stack: R, RStudio, Data Cleaning, Data Preprocessing, Feature Engineering, Time Series Analysis, Machine Learning, XGBoost, LightGBM, CatBoost, Hyperparameter Tuning, Model Evaluation.

GitHub

Online Furniture Store using Node JS & PostgreSQL

This project aims to develop a comprehensive online office furniture store, complete with a database and web application. The project involves designing and implementing a database schema, developing front-end and back-end functionalities, and integrating these components to create a functional and user-friendly system.

Tech Stack: Node JS, Express, PostgreSQL, HTML, CSS, JavaScript, Bootstrap, RESTful APIs, CRUD Operations, Database Design.

GitHub