| | | 20,000+ Fresh Resumes Monthly | |
|
|
| |
Click here or scroll down to respond to this candidateCandidate's Name
Data Scientist with 3+ YoE driving business impact via ML & Analytics, MS from CU Boulder. Boulder, CO EMAIL AVAILABLE PHONE NUMBER AVAILABLE LINKEDIN LINK AVAILABLE GitHub Tableau Public SUMMARYAnalytical, collaborative and results-driven data science professional with 3+ years of experience driving digital transformation in Manufacturing and Supply chain for Fortune 500 clients. Skilled in partnering with cross-functional teams to develop and deploy end- to-end AI/ML solutions that optimize operations and deliver measurable business impact. Proficient in Statistical Modeling, ML & NLP. SKILLSProgramming Python (Pandas, NumPy, Matplotlib), R (Tidyverse, ggplot), SQL (OracleSQL, MySQL), SAS, MATLAB, PySpark, C Framework TensorFlow, Keras, PyTorch, Scikit-learn (Classification, Regression, Clustering), Azure ML Studio, AWS SageMaker GenAI & NLP Large Language Models (GPTs, Llama), Transformers, BERT, Hugging Face, LangChain, Embeddings, VectorDB Cloud & Database Microsoft Azure (Azure ML, Azure Functions, Databricks), AWS (SageMaker, EC2, S3, Lambda, Redshift) Snowflake Tools & Platforms Tableau, Microsoft Power BI, Looker, Azure Synapse, Data Factory, AutoML, Airflow, Git, Docker, Kubernetes EXPERIENCEEmerson Electric Boulder, COData Scientist May 2023 May 2024Calibration Prediction Model Developed an ML model using Random Forest and XGBoost to predict equipment failure during manufacturing with 95% accuracy and a 0.9 F1 score, enabling early intervention and improving final quality control pass rates. Applied PCA and Lasso Regression for feature selection reducing a 280+ column dataset and improving model performance. Engineered ETL pipelines with PySpark in Azure Synapse to integrate 1M+ records from 4 data sources, ensuring scalability. Deployed model on Microsoft Azure using Docker & CI/CD, enhancing cross-platform integration, contributing to $2M revenue. Inventory Optimization Designed a safety stock prediction (regression) model using statistical techniques in Python on Azure Machine Learning platform to minimize stockouts and excess inventory, enhancing operational efficiency and reducing holding costs by 15%. Conducted A/B testing on inventory strategies, projecting a 20% reduction in overstock and a 10% improvement in turnover. GenAI Chatbot and AI Workshops Fine-tuned GPT-3.5 Turbo LLM with prompt engineering, embeddings and RAG for a custom new hire AI-chatbot. Facilitated 6 monthly ML workshops for 300+ employees to boost cross-functional AI collaboration & identify AI/ML use cases. University of Colorado Boulder Boulder, COData Science Research Assistant Jan 2023 May 2023 Built R package combining ARIMA, Prophet, LSTM for auto time series forecasting with configurable model evaluation & selection. Created automated functions for tuning, testing models and selecting optimal predictor based on AICc, BIC, RMSE metrics - outputting parameter values, plots and comparative performance indicators to enable accurate deployments. Honeywell Pune, IndiaData Analyst Aug 2019 Jul 2022 Utilized Honeywell Historian Analytics Platform to conduct Exploratory Data Analysis on process plant data (Oil and Gas, Life Sciences), identifying key trends and anomalies that reduced nuisance alarms by 90% and improved operational efficiency. Executed SQL CRUD operations on 800K row database, enhancing data modeling and warehousing to facilitate advanced analytics. Developed Tableau dashboards and BI reports, tracking KPIs to cut resource downtime by 20% and increase insight speed by 30%. Boosted project results via on-site collaborations in 3 countries, demonstrating global adaptability & cross-functional teamwork. Developed & tailored Operational Technology applications (DCS, PLC, SCADA) through full SDLC, enhancing operational efficiency. Led 4-person team, achieving 2% budget savings and on-time completion, earning "Going Beyond and Above Expectation" award. EDUCATIONUniversity of Colorado Boulder, Boulder, CO Aug 2022 May 2024 Master of Science in Data Science GPA: 3.97/4.0Focused Coursework: Advanced Statistics, Deep Learning, Machine Learning, Data Mining, NLP, Big Data Architecture Vishwakarma Institute of Technology, Pune, India Jul 2015 - May 2019 Bachelor of Technology in Electrical and Computer Engineering GPA: 3.76 /4.0 PROJECTSStock Prediction using Time series Forecasting & Sentiment Analysis Jan 2024 Apr 2024 Developed a stock prediction model using ARIMA, RNN (LSTM) algorithms, integrating TensorFlow/Keras for deep learning and FinBERT for sentiment analysis. Improved accuracy through ensemble methods and showed the comparative results on PowerBI. Course Recommendation and Planner Platform Dec 2022 Mar 2023 Developed a GCP-hosted course recommendation platform using Named Entity Recognition for user intent analysis and a Sparse Similarity Matrix to match queries with relevant courses, enhancing personalized recommendations through user-friendly WebUI. Predicting Housing Prices with Regression Analysis Jan 2023 Feb 2023 Streamlined data pipeline creation and model optimization across linear, ridge, lasso, and random forest regressions, achieving R-squared of 0.9 and MSE of 900 through focused hyperparameter tuning and cross-validation for better prediction accuracy. |
