RATEEB YEHYA

linkedin.com/in/rateebyehya https://github.com/rateebyehya ad26iv@r.postjobfree.com 424-***-**** Los Angeles, CA EDUCATION

UCLA ANDERSON SCHOOL OF MANAGEMENT Los Angeles, CA Master of Science in Business Analytics (GPA: 4.0) Expected December 2023

• Machine Learning, Data Management, Optimization, Business Fundamentals, Operations, Customer, Competitive Analytics AMERICAN UNIVERSITY OF BEIRUT Beirut, LB

Bachelor in Civil Engineering with a Minor in Mathematics (GPA: 3.7) June 2019

• Statistical Modeling, Probability Distributions, Probability Simulations, Complex Analysis, Simulation TECHNICAL SKILLS

Technical Languages: Python (Keras, Scikit-learn, Numpy, Pandas, Seaborn, Matplotlib), SQL, R Studio (Tidyverse, R Markdown) Analysis & Modeling: Machine Learning, Exploratory Analysis, A/B Testing, Statistical Modeling, Simulation, Real Time Analytics Software: Tableau, Jupyter, Excel, Google sheets, MySQL, Adobe Analytics, SingleStore, Hadoop, Hive, SnowFlake, AWS, S3 Bucket PROFESSIONAL EXPERIENCE

Cedars-Sinai Los Angeles, CA

Artificial Intelligence Developer September 2023 – January 2024

• Led the development of Meddy, an application simplifying communication between medical professionals and databases, providing instant answers without the need for manual SQL queries. It converts spoken questions to text, then translates them to SQL, retrieves the answers, and communicates them back via text or speech.

• Leveraged LangChain and Azure GPT-4 for Meddy’s development Cedars-Sinai Los Angeles, CA

Data Scientist June 2023 – September 2023

• Led a Cedars-Sinai project that predicts patient readmissions from clinical notes, presenting results to the Vice President of the Advanced Analytics group as well as other senior managers

• Preprocessed text data using WordTokenizer and Lemmatization, cleaning it for exploratory data analysis and modelling

• Joined, pivoted, and restructured multiple tables to obtain a single table that contains all information about each patient

• Utilized Tableau for data exploration and visualizations, creating 8 interactive dashboards that track readmission types and dates, word counts, n-grams, and other demographic features for each patient

• Developed five Bag-of-Words Models to predict patient readmissions from clinical notes, with one model (RIDGE) achieving an AUC score of 0.91

• Fine-tuned two large language models (ClinicalBERT and GPT) from Hugging Face, using Cedars-Sinai High Performance Computing Cluster (HPCC) and parallel processing capabilities, resulting in AUC scores of 0.93+.

• Wrote bash scripts to allocate GPUs, RAM, and CPUs on Cedars-Sinai High Performance Computing Cluster 01TUTOR – E-learning platform that provides tutoring services to undergraduate students Middle East & Canada CEO & Founder July 2019- September 2022

• Designed and developed 15 online courses, continuously capturing customer feedback for product development

• Leveraged Data Analytics to identify most useful quizzes, resulting in additional student engagement by 42%

• Segmented customer base based on recency, frequency, and monetary value, tailoring products and discounts to each segment.

• Surveyed 200+ customers to assess product features and collect insights for product development

• Led a team of five outstanding students in designing pre-recorded online courses, increasing revenues by over $30K/year

• Conducted market research on 1K students in three markets to identify purchasing power, optimizing course prices, increasing revenue by 15%

Reimann’s Hypothesis Los Angeles, CA

Mathematical Researcher on Prime Number Distribution January 2004 – Present

• Attempting to solve one of the seven Millenium problems in Mathematics, the Reimann Hypothesis, which if proved, uncovers the secret of prime numbers.

• Writing an 80-page book that I am planning to publish soon under the supervision of Terrance Tao at UCLA Anderson.

• Bridged the connection between a solution to the prime number distribution and modeling random noise.

• Discovered the circle of unity, where the integer space is trying to regenerate itself, but never could.

• Discovered the relationship between the prime number distribution and Euler’s number, imaginary number, and . MACHINE LEARNING & ANALYTICS PROJECTS

Real-Time Sentiment Analysis on Twitch Live Streaming Comments March 2023 – June 2023

• Scraped real-time comments on Twitch Live Streams using Twitch APIs. Ingested real-time data in Snowflake. Used Python for data cleaning and wrangling. Used ChatGPT APIs to perform sentiment analysis, updating Snowflake Database with sentiment results. Connected Snowflake to Tableau for real-time visualizations of KPIs and sentiment analysis. Amazon Building Item-Based Recommendation System September 2022

• Generated recommendations for 25K Amazon products using NLP. Presented results to Senior Analytics and Insights Manager CERTIFICATES & SPECIALIZATIONS

IBM Machine Learning Specialization Certificate (IBM, 2022) GOOGLE Data Analytics Professional Certificate (Google, 2022) SQL Basics for Data Science (UCDAVIS, 2022) TensorFlow Developer Professional Certificate (DeepLearning AI, 2022) AWS Fundamentals Specialization Certificate (Amazon, 2023) Snowflake Badge 1: Data Warehousing Workshop (Snowflake, 2023)

Contact this candidate