Kalki Prasad A

I am a Highly motivated and ambitious Data Scientist with a robust background in statistical analysis, machine learning algorithms, and data manipulation techniques. Expertise in Python, SQL, and Big Data technologies, coupled with a proven track record of developing and deploying advanced machine learning and deep learning models for natural language processing and predictive analytics. Committed to delivering scalable data-driven solutions that tackle complex business challenges while remaining informed on industry trends.

Developed and compared machine learning models (Logistic Regression, Decision Tree, Random Forest, XGBoost, K-Nearest Neighbors, and Naive Bayes) to classify bank clients based on subscription to term deposits. The project involved data preprocessing, feature engineering, and performance evaluation across models to interpret results and select the most effective algorithm.

Developed a deep learning model using TensorFlow and transfer learning with MobileNetV2 to classify images of bean leaves into three categories: Healthy, Angular Leaf Spot, and Bean Rust. Leveraged a pre-trained model, optimized performance using Early Stopping, and achieved robust classification supported by detailed evaluation metrics like precision, recall, F1-score and accuracy of 91%

Developed a deep learning model using LSTM to predict the next word in a text sequence based on Shakespeare's Hamlet. Leveraged TensorFlow & Keras for model development and deployment. Key highlights include data preprocessing, model training, prediction, and deployment using Streamlit. Achieved accurate predictions by capturing long-term dependencies in the text data.