Data Scientist
Resume:
Ainesh Pandey
AI and Machine Learning Leader
PROFESSIONAL EXPERIENCE
Lead Product Data Scientist, Dataherald, Los Angeles, CA, USA May 2022 – Present
• Led internal data science initiatives supporting marketing and product analytics o Improved top-of-funnel for data providers by conducting causal inference analysis (ranging from 26% to 67% lift) o Standardized ~98.7% of geographic text across data providers with a customized fuzzy text matching algorithm
• Solutions architect for text-to-SQL gen AI product (9 corporate clients), propelled customer journey for 100s of customers
• Grew Data Science team (3-5 ICs) maintaining 100s of pipelines, SmartVizs, engaged in R&D for text-to-SQL tool Lead Data Scientist, IBM, Data Science and AI Elite, San Francisco, CA, USA Jan 2018 – May 2022
• Devised machine learning solutions for internal/external and international clients o Developed joint classification/regression model to determine ideal factory settings for a large distributor, reduced plastic consumption by 12% while maintaining breakage rate, resulting in savings of ~$1.5 million annually o Implemented point-of-sale recommendation system for major retailer, achieving conversion rate of ~12% o Identified churn risk (92% accuracy) for large LATAM telecom provider, trained neural net to suggest next-best-offer
• Led the ideation and execution of two IBM Data Science Accelerators, capturing 6 deals valued at $1m+ Data Scientist, Kaiser Permanente, Pleasanton, CA, USA May 2017 – Dec 2017
• Built sentiment analysis tool for healthcare reviews (~88% accuracy), integrated cross-enterprise through Flask app Graduate Data Analyst, BBC Worldwide, Pittsburgh, PA, USA Apr 2017 – Dec 2017
• Ensembled 5 different models (stepwise regression, logistic regression, SVM, decision tree, random forest) to score unlicensed shows, surpassing target MSE of 0.7 (scored at 0.43)
• Helped optimize marketing mix model to maximize anticipated ROI (4.8x) Software Developer Intern, Morgan Stanley, New York, NY, USA May 2015 – Aug 2015
• Penned SRS (Software Requirements Specifications) and the WSDL for new banking feature
• Built a desktop password encryption/decryption tool for debugging purposes PROGRAMMING AND DEVELOPMENT SKILLS
• Programming Python, R, Java, C++, C#, SQL, NoSQL
• Data Science/ML pandas, numpy, scikit-learn, pyspark, pytorch, tensorflow, jupyter notebook, seaborn, lime, shap
• AI and LLMs deep learning, LangChain, OpenAI, Mistral AI, Vanna AI, SQL-Coder, Llama-2, Claude
• Data Warehouses Azure, AWS, Snowflake, BigQuery, Databricks, PG, Pinecone, Cassandra, Chroma, ClickHouse EDUCATION
Carnegie Mellon University, H. John Heinz III College Pittsburgh, PA, USA MS in Information Systems Management - Business Intelligence and Data Analytics Arizona State University, Barrett, The Honors College Tempe, AZ, USA BS in Computer Science, Ira A. Fulton School of Engineering BS in Business Data Analytics, W.P. Carey School of Business NATIONAL AWARDS
National Institute of Child Health and Human Development Aug 2021 – Nov 2021 Decoding Maternal Morbidity Data Challenge
• Developed risk index using live data from diverse group of pregnant women to identify the risk of morbidities
(hypertension, post-partum anxiety or depression, preeclampsia) with high F1 scores ranging from 0.63 to 0.76
• Ranked first nationally in both the main prize ($50k) for an innovative solution and the auxiliary prize ($10k) for effectively addressing adverse impact on minority women SCHOLARSHIPS
• Boren Scholarship for International Study, IIT Bombay
• MISM Full-Tuition Scholarship, Carnegie Mellon University
• New American University National Scholar, Full-Tuition, Arizona State University San Diego, CA
********@*****.***
Contact this candidate