Hey there I’m Yash Malviya—a Data Science grad student @ WPI by day, an AI Developer by night, and a full-time believer that data can solve (almost) everything. I’m the guy who’ll geek out over neural networks at Dunkin ☕, debate the Interstellar movie during the Steve Harvey show, and still ship a scalable ML model before the deadline. Expertise: 🔍 Data Science & Machine Learning: - Built predictive models that forecast sales 📈 (boosted revenue by 25% for TCS—and it turns out machines can predict the future). -Taught AI to summarize text 🤖📝 (Hugging Face + spaCy) and even tried teaching it sarcasm. Work in progress. 💼 MLOps & Scripts: -Proficient in Python, SQL, and dad jokes. -Configured Spark/Hadoop clusters into every BigData pipeline. -Automated MLOps pipelines (CI/CD) with Docker/Kubernetes with some Bash scripts, so I can sleep peacefully at night, every time I deploy a Machine Learning model. 📊 Business Intelligence: -Utilized my Intelligence in Business Intelligence to transition BI systems from the Prenatal to Sage Stage on a scale of BI Maturity. -Adept at creating KPI dashboards and reports using Tableau, Power BI, QlikView / Quicksight, and many more just figuring out which is best to use so I don't have to cry over specific Features of these tools. -Fluent in SQL and solving Data extraction problems as ChatGPT doesn't always give the right queries for complex problems. 🌐 Industry Impact: -As Research Assistant and Data Science Intern - Translated caffeine into code ☕ while researching AI/ML solutions to improve healthcare data interoperability (yes, I made HL7/FHIR standards sound cool). Partnered with Availity Clinical Solutions to design AI-driven workflows that boosted system efficiency by 20%. Tools: Python, TensorFlow, PyTorch, FHIR APIs -As Data Scientist for Tata Consultancy Services for 2+ years - Built machine learning models that predicted sales trends accurately, for a Retail Giant in Dubai (Landmark Group). Results? 25% revenue boost and 19% higher sell-through rates. Automated reporting dashboards (Power BI) that saved analysts 10+ hours/week. Tools: Python, sci-kit-learn, SQL, AWS SageMaker -As Data Engineer at Xoriant - Deployed real-time ELK Stack dashboards (Elasticsearch, Logstash, Kibana) Optimized Spark pipelines to process TBs of data faster than the average cat . Tools: Spark, Hadoop, Docker, Kubernetes. PS: I’ve cried over mislabeled data. I will reference The Office during meetings. Let's connect & Chat!