Architecting production-grade ML systems and healthcare analytics. Specialized in deep learning, time series forecasting, and deploying scalable AI solutions.
import tensorflow as tf
from sklearn.model_selection import train_test_split
# Load and preprocess data
model = tf.keras.Sequential([
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dropout(0.3),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(1, activation='sigmoid')
])
# Compile and train
model.compile(
optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy']
)
I'm a results-driven Data Scientist specializing in production-grade ML systems and healthcare analytics, with a passion for transforming complex datasets into actionable insights.
Currently pursuing my Bachelor of Arts (Hons) in English from Delhi University, I've developed expertise in architecting end-to-end solutions—from data validation to deployment. My work focuses on time series forecasting, deep learning pipelines, and RESTful API development.
I believe in the power of advanced statistical modeling and interactive dashboards to drive business decisions and create meaningful impact in healthcare and beyond.
Healthcare facility capacity monitoring framework with ARIMA time series forecasting. Features real-time Streamlit dashboard with KPI cards and interactive Plotly visualizations.
I worked on a workforce attrition analytics project where I analyzed employee data to identify key attrition patterns and risk factors using statistical testing. I built machine learning models (Logistic Regression, Random Forest, XGBoost) with Optuna tuning to predict attrition risk. Additionally, I developed an interactive Streamlit dashboard for real-time insights, risk visualization, and HR decision support.
ML model for chronic heart disease prediction with comprehensive feature engineering. Deployed as a production-ready FastAPI service on Render.
LightGBM-based prediction model with RESTful API architecture. Containerized using Docker for scalable deployment and consistent environments.
Artificial Neural Network for multi-class classification with input validation. Deployed as production API demonstrating end-to-end ML workflow.
I'm always interested in hearing about new projects, opportunities, and collaborations. Whether you have a question or just want to say hi, feel free to reach out!