Skip to content

Basanuri Ranjitha

Aspiring Machine Learning Engineer • Hyderabad • r*****************@gmail.com • +91*******908 • drivetube.ai/•••••

Career Objective

Machine Learning Engineer with 0 years of experience leveraging Python, Java and core ML techniques to build classification and computer-vision models. B.Tech in Computer Science (2021–2025) with hands-on projects in SMS spam detection (NLP) and real-time CNN-based forest fire detection. Strong foundation in data structures & algorithms, object-oriented programming, SQL and Git; seeking an entry-level ML / software engineering role to contribute to model development, data pipelines and production-ready solutions.

Education

Megha Institute of Engineering and Technology
Bachelor of Technology in Computer Science • Hyderabad, India • 2021 – 2025
TSWREIS School Junior College (Girls)
Intermediate • Hyderabad, India • 2019 – 2021
TSWREIS School Junior College (Girls)
SSC • Hyderabad, India • 2018 – 2019

Technical Skills

Programming Languages: Python,Java,C,JavaScript
Frameworks and Libraries: NumPy,Pandas,scikit-learn,OpenCV,TensorFlow,Keras,Matplotlib
Databases: SQL,MySQL,DBMS
Data and Analytics: Machine Learning,Deep Learning,Natural Language Processing,Feature Engineering,Model Evaluation
Tools and Methodologies: Git,GitHub,VS Code,Jupyter Notebook
Web & Frontend: HTML5,CSS3
Core Concepts: Data Structures & Algorithms,Object-Oriented Programming

Projects

SMS Spam Filtering – ML Comparative Analysis | Nov 2024 – Nov 2024
Tools Used: Python, Pandas, NumPy, scikit-learn, NLP, Matplotlib
  • Designed and implemented an end-to-end SMS spam detection pipeline: data ingestion, text preprocessing, feature extraction and model training using Python and Pandas.
  • Applied NLP preprocessing (tokenization, stop-word removal, TF-IDF) and engineered features to improve classifier input quality.
  • Trained and compared multiple classification models (e.g., logistic regression, decision trees, ensemble methods) using scikit-learn and evaluated with accuracy, precision, recall and F1-score.
  • Selected best-performing model based on F1-score and produced confusion-matrix and ROC visualizations using Matplotlib to communicate trade-offs.
  • Implemented reproducible experiments and model-selection scripts with versioned notebooks and Git for traceability.
Forest Fire Detection & Protection using CNN | May 2025 – May 2025
Tools Used: Python, OpenCV, NumPy, Keras, TensorFlow, Deep Learning, Matplotlib
  • Developed a real-time forest-fire classification system that processes image and video frames using OpenCV and a convolutional neural network implemented with TensorFlow/Keras.
  • Built data preprocessing and augmentation pipelines (resizing, normalization, augmentation) to increase training robustness on limited imagery.
  • Trained and validated CNN models, monitored loss/accuracy curves, and tuned hyperparameters to improve detection recall for early fire signs.
  • Integrated geolocation mapping logic and a basic alerting mechanism to demonstrate actionable responses when fire is detected.
  • Created visualization dashboards with Matplotlib to present model performance, false positives analysis and fire-risk heatmaps.

Certifications

Programming Essentials in Python — DataPoint
Programming Essentials in C — Cisco
Cybersecurity virtual Program — Mastercard via Forage
Data Analytics Essentials — DataCamp

Powered by Drivetube · Create your own profile at drivetube.ai