Marwah Faraj
San Jose,CA
Summary
Dynamic Senior Data Scientist, specializing in applying machine learning (ML), statistical analytics, and data science methodologies to drive significant business insights and outcomes. Expert in building end-to-end projects using machine learning state of the art. Skilled in engaging cross-functional teams to understand needs, develop relevant solutions, and enhance data-driven decision-making processes. Committed to leveraging advanced analytics to improve operational efficiencies and business strategies.
Overview
16
16
years of professional experience
1
1
Certification
Work History
AI/ Machine Learning Senior Engineer/ Data Scientist
Geico
Remote
09.2023 - Current
- Led the creation of an AI-powered chatbot using advanced natural language processing techniques, achieving a 95% accuracy rate
- This tool significantly improved customer service efficiency and user satisfaction by providing timely and accurate responses to inquiries
- Spearheaded the implementation of the End-to-End Ops Data platform, significantly enhancing data science algorithm scalability for the Sourcing function
- Enhanced automated emails process through experimentation by implementing AB testing, embedding within stakeholder domains to develop a self-serve experimentation framework
- This initiative led to a 30% increase in the velocity of the customer engagement process, enabling rapid, data-driven decision-making and significantly improving the performance of consumer-facing products
- Built visualization tools and reports that provided actionable insights, enabling the business to rapidly adapt to market changes and optimize inventory management.
BI engineer, Data Scientist
The Walt Disney Company
Remote
12.2021 - 06.2023
- Utilized advanced statistical techniques and ML algorithms to improve model performance and resolve data inconsistencies, enhancing decision-making processes
- Successfully led discussions with cross-functional teams to understand business needs, developing and implementing data-driven solutions that were immediately adoptable
- Successfully applied advanced statistical techniques and blending of algorithms (GRB, Extra tree regressor, XGboost, LGBM, Random Forest) to predict the number of impressions for the 2023 CFB season across multiple platforms (ACCN, SCEN, ESPN+, ESPN1, ESPN2, ESPN3, ESPNU), achieving an accuracy rate of 96%
- Led an end-to-end project utilizing the Extra Tree Regressor algorithm to forecast the number of impressions per sport for the 2023 NBA season, achieving a 91% accuracy rate
- Constructed a Tableau dashboard to visualize the real-time performance of predictive models, seamlessly connecting to Snowflake for data pipeline-based integration.
Senior Data Scientist
Commission of Integrity
Baghdad, Iraq
03.2017 - 09.2020
- Worked on the 'go-case' program on growing data of millions rows that was built by the United Nations and got predictions of how to enhance the productivity of the investigators' performance
- Built unsupervised machine learning models and prepared reports after making a statistical reading on data.
Senior Data Scientist
Commission of Integrity
Baghdad, Iraq
11.2014 - 03.2017
- Created a data pipeline using Python to automate the analysis of sensory tests, reducing results turnaround time by 75%
- Worked on big data of thousands of rows obtained from the 'go-case' program that was built by the United Nations organization and built unsupervised machine learning models and used statistical methods to analyze data and provide technical recommendations of where to increase the work.
Jr. Data Scientist
Commission of Integrity
Baghdad, Iraq
10.2013 - 11.2014
- Used Matplotlib and Seaborn to deliver effective data visualization presentations of supervised machine learning models and recommendations to other departments to enhance their performance depending on department work field, the area, and how the court did work which sometimes could get the work done due to the bad circumstances in Iraq
- Generated status reports for all savings projects at the site using Python for data visualization and machine learning algorithms like logistic regression and random forest classifier for prediction of the target requested by the client and presented to the Auditing office on a monthly basis.
Presentation Designers/Report Writer, Data Analyst
Women's leadership institute
Baghdad, Iraq
09.2008 - 10.2013
- Designed a presentation in Google Slides from unstructured data to present it in the workshops and trainings held by the institute for over 50 attendance and ensure that the audience receives the right message
- Analyzed data that is routinely collected by the institute and wrote weekly and annually reports for the activities performed by the institute.
Education
Data Science Immersive -
Galvanize, Inc
San Francisco09-2021
Bachelor's Degree (BS) - Computer Science
University of Baghdad
01.2008
Skills
Technical skills:
- Programming Languages: Proficient in Python (Numpy, Pandas, Sci-kit Learn, TensorFlow, Keras), SQL, PostgreSQL
- Machine Learning/Deep Learning: Comprehensive knowledge Linear and Logistic regression, Decision Tree, Random Forests, Extratree regressor,XGBoost, LGBM,Pycarets, KNN, Gradient Boosting, Neural Networks (MLP, CNN), Natural language processing (NLP), Transfer Learning, Tensorflow, Keras, PCA, Auotoml, Flaml, Tpot, SMOTER, SMOGN
- Data Visualization: Matplotlib, Seaborn, Tableau, Power BI
- Tools and Platforms: GitHub, Jupyter Notebook/Lab, VSCode, Flask, FastAPI, Streamlit, Postman, AWS, Docker, Azure, Snowflake, Salesforce cloud
Professional Skills: Technical Reporting, Project Research, Attention to Detail, Technical Expertise, Cross-Functional Collaboration
Projects
- MS Disease Detection
- The Next Pitch: Unlocking the Future of Sales
- Fraud Detection, GitHub
- Pose Estimation Applications/ Computer Vision
- Arabic Tweets Sentiment Analysis
- Automobile Price Prediction
Certification
- AI Bootcamp: nocode.ai
- Design Powered by Data: Getting Started with UX Web Analytics, LinkedIn Learning 2023
- Artificial Intelligence Foundations: Thinking Machines, LinkedIn Learning 2023
- Deep Learning: Getting Started, LinkedIn Learning 2023
- Machine Learning Foundations: Linear Algebra, LinkedIn Learning 2023
- Advanced NLP with Python for Machine Learning, LinkedIn Learning 2023
- Generative Al for Creative Pros: Opportunities, Issues, and Ethics, LinkedIn Learning 2023
- Complete Python Mastery, Code With Mosh, 2021
- Python Basics for Data Science, IBM, 2021
- Learning SQL Programming, LinkedIn Learning 2021
- Machine Learning with Scikit-Learn, LinkedIn Learning, 2021
Timeline
AI/ Machine Learning Senior Engineer/ Data Scientist
Geico
09.2023 - Current
BI engineer, Data Scientist
The Walt Disney Company
12.2021 - 06.2023
Senior Data Scientist
Commission of Integrity
03.2017 - 09.2020
Senior Data Scientist
Commission of Integrity
11.2014 - 03.2017
Jr. Data Scientist
Commission of Integrity
10.2013 - 11.2014
Presentation Designers/Report Writer, Data Analyst
Women's leadership institute
09.2008 - 10.2013
Data Science Immersive -
Galvanize, Inc
Bachelor's Degree (BS) - Computer Science
University of Baghdad
Similar Profiles
Julissa F BocanegraJulissa F Bocanegra
Claims Adjuster at GEICOClaims Adjuster at GEICO
Robert FikarRobert Fikar
High Performance Associate at GEICOHigh Performance Associate at GEICO
Oona MooreOona Moore
Insurance Claims Representative at GEICOInsurance Claims Representative at GEICO
Yolanda LujanYolanda Lujan
Bodily Injury Claims Adjuster at GEICOBodily Injury Claims Adjuster at GEICO
Abraham ContrerasAbraham Contreras
Telecommunication Foremen Lineworker at Fibertel, LLC Quanta ServicesTelecommunication Foremen Lineworker at Fibertel, LLC Quanta Services