Aishvarya Salvi profile picture

Hello, I'm

Aishvarya Salvi

Data Science Graduate

My LinkedIn profile My Github profile

Get To Know More

About Me

Profile picture
Experience icon

Experience

3+ years
Software Engineering & Test Automation

Education icon

Education

MS in Data Science
BE in Computer Science

Data-driven professional with 3+ years of experience in analytics, machine learning, and data engineering. Proficient in Python, SQL, Spark, Kafka, and GCP, with expertise in building scalable ML pipelines and recommendation engines. Adept at real-time data processing, model deployment, and interactive dashboard development. Strong foundation in MLOps, CI/CD, and containerization using Docker, Kubernetes, and Jenkins. Passionate about delivering actionable insights and production-ready solutions from complex datasets.

Arrow icon

Explore My

Skills

Programming Languages

Python SQL Java R C/C++ PostgreSQL Oracle Database SQLite

Frameworks & Libraries

Pandas NumPy Matplotlib Seaborn Scikit-learn TensorFlow XGBoost Random Forest Logistic Regression Streamlit FastAPI Selenium WebDriver Karate API TF-IDF Apache Spark

Developer Tools & Platforms

Git GitHub Docker Docker Compose Kubernetes Jenkins GitHub Actions VS Code PyCharm IntelliJ Eclipse JIRA Power BI Tableau Browser Developer Tools GCP AWS

Browse My Recent

Projects

E-Commerce Product Recommendation System

E-Commerce Product Recommendation System

Engineered a full-stack ALS-based recommendation engine on 2.7M+ RetailRocket events with optimized sparse matrix processing and real-time predictions, deploying a FastAPI backend + Streamlit frontend fully containerized with Docker Compose for scalable, production-ready delivery.

Real-Time Analytics and Churn Prediction Pipeline

Real-Time Analytics and Churn Prediction Pipeline

Built a real-time streaming pipeline processing 10K+ Kafka events per min with Spark Structured Streaming, storing data in PostgreSQL and delivering Logistic Regression churn predictions with 85% accuracy via FastAPI in less than 200ms, and developed a Streamlit dashboard with 15-second auto-refresh.

Heart Attack Risk Prediction Pipeline

Heart Attack Risk Prediction Pipeline

Designed and deployed a machine learning pipeline for heart attack risk prediction, performing data wrangling, feature engineering, and exploratory analysis on 20+ clinical and lifestyle variables, implementing Logistic Regression, Random Forest, and XGBoost models, managing 7+ ML experiments with MLflow/DagsHub.

Arrow icon

Get in Touch

Contact Me