Hi, I'm Rambabu Bevara, a passionate Data Analyst & Machine Learning Enthusiast who loves turning raw data into clear, actionable insights.
I work with Python, SQL, Power BI, and Excel to clean, analyze and visualize data. On the machine learning side, I build models for regression, classification, recommendation systems, NLP, and computer vision.
Some of my key projects include House Price Prediction, Beauty Product Recommendation, Remote Worker Mental Health Prediction, Sentiment Analysis on Clothing Reviews, and Image-based Similarity & Object Detection.
I enjoy learning by building end-to-end projects – from data collection and EDA to model deployment on Streamlit. I’m actively looking for opportunities as a Data Analyst / Junior Data Scientist.
Exploratory Data Analysis on real estate data combined with weather and disaster-related factors, finding patterns that affect property demand and pricing.
Source CodeHybrid recommendation engine using TF-IDF, cosine similarity, and user preferences to recommend relevant beauty products.
App Link Source Code
Machine learning model that predicts potential mental health risk for remote workers using survey-based features.
App Link Source Code
Regression model built using ensemble learning (Random Forest) to predict house prices with strong R² performance.
Source Code
NLP pipeline to classify customer reviews into sentiment classes using TF-IDF features and ML models.
Source Code
Deep learning image classifier to identify different tribes / cultural groups using CNN-based models and transfer learning on image datasets.
Source Code
Computer vision project using CNN embeddings and cosine similarity to retrieve visually similar footwear images.
Source Code
Object detection pipeline using deep learning to detect and classify necklace types with bounding boxes.
Source Code
Core programming language for all data science workflows including data analysis, automation, and machine learning model development.
Experience building predictive models using regression, classification, clustering, and ensemble methods with Scikit-learn.
Hands-on experience with neural networks, CNNs, and RNNs using TensorFlow and PyTorch for AI applications.
Implemented NLP models for sentiment analysis, summarization, and query based text generation using BERT and BART.
Explored LLMs, prompt engineering, and fine tuning using Hugging Face and OpenAI APIs to build intelligent applications.
Developed interactive dashboards to visualize key metrics and business insights for data driven decision making.
Skilled in database creation, SQL queries, joins, and integrating data pipelines with Python and analytics tools.
Strong command of Excel for data analysis, pivot tables, Power Query, and quick visual insights.
Processed and transformed messy data into structured datasets using Python libraries like Pandas and NumPy.
Applied statistical concepts like distributions, correlation, and hypothesis testing for analytical insights.
Performed univariate, bivariate, and multivariate analysis to uncover patterns and data insights.
Created advanced visualizations using Matplotlib, Seaborn, Plotly, and Power BI for impactful storytelling.
Used analytical reasoning to identify data driven solutions and optimize business or model outcomes.
Evaluated models using metrics like RMSE, ROC AUC, Precision, Recall, and F1-Score to ensure high accuracy.
Transformed and created features to boost model performance and extract more predictive insights.
Deployed models using Streamlit locally and on the cloud for real time accessibility and interactivity.
Built ETL pipelines, automated data workflows, and integrated structured and unstructured data sources.
Turned complex datasets into actionable stories using visual reports and dashboard presentations.
Collected and analyzed large scale data using BeautifulSoup and Selenium for insights and automation.
The ability to deploy, scale, and manage machine learning models and data pipelines on cloud platforms essential for real world, production level data science solutions.