Ibrahim S Eldivan

About Ibrahim S Eldivan

I am a Research / Data Scientist and have 10+ years of experience in the data-driven field with a strong background in Statistics, Data Science, working with various programming languages (Python, SQL, etc.), specialized in Natural Language Processing, conduct large scale analysis by using Hadoop, Apache, Spark, and familiarity with Predictive Modeling. With my Ph.D. in the field of Criminal Justice and experience in data analysis and statistics, I have been teaching Data Analysis & Statistics, Research Methods to graduate and undergraduate students at Rutgers University. I am passionate to expand my analytic skills in Data Science and believe that dealing with data and applying Machine Learning techniques, making predictions give definitive solutions to real-life problems. TECHNICAL SKILLS • Data Visualization, Statistical Machine Learning Algorithms, Linear and Logistic Regression, Decision Tree, K Means clustering, Support Vector Machine (SVM), Random Forest, XGBoost, Ensemble methods, Big Data, NLP • Tools: Jupyter Notebook, NumPy, Pandas, SciPy, Sci-kitLearn, Pyspark, Statsmodel, TensorFlow, NLTK, RE, BeatifulSoup4, Seaborn, Matplotlib, Plotly, Cufflinks, Choropleth, Times-Series Forecasting, GitHub/Git, Spark, AWS Cloud Services, Pytorch, Tensorflow, Teapot, H2O, AutoML, Orange, Tableau, Alteryx • Programming: Python, MySQL, PostgreSQL

Experience

1. Manager, Mlops Team

   PepsiCo

   Sep 2021 — Present · Purchase, NY, US

   Git and GitHub • Python software development; developing applications that utilize industry-standard practices for composition and modularity; debugging and following tracebacks • Querying SQL-compatible databases using Snowflake • Interacting with resources on AWS (Batch, S3) • Regularization • Hyperparameter optimization • Strong communication and collaboration skills to iterate productively with the insights team • TensorFlow functional API or equivalent •…