Ayoub Berrag | Data Scientist

Hi, I'm Ayoub Berrag.

A

My passion for data science, combined with technical expertise and strong soft skills such as communication and problem-solving, allow me to deliver impactful solutions and drive data-informed decision making.

About

As a highly skilled Data Scientist, I have a passion for using data to drive informed decisions. With a Master's degree in Big Data Analytics and Smart Systems and a Bachelor's degree in Mathematics and Computer Science, I possess technical expertise in data analytics, business intelligence, data mining, big data, and programming languages such as Python, R, Java, C++, and SQL. Additionally, my strong soft skills including teamwork, time management, problem-solving, creativity, and leadership have enabled me to effectively lead teams and collaborate with cross-functional groups. I am dedicated to delivering impactful solutions that enhance productivity and drive business growth..

Data Analysis tools PowerBi, Tableau, Excel.
Business Intelligence: Talend, QlikView, ETL, Data Warehouse
Big Data: Apache Ambari, Hadoop and HDFS, MapReduce, HBase and Apache Spark.
Data Mining: Supervised and unsupervised Learning, Deep Learning, Computer Vision, Federated Learning, Case Study.
Languages: Python, SQL, C, C++, R

I am seeking a challenging position that allows me to combine my skills in Data Analysis with opportunities for professional development, interesting experiences, and personal growth.

Experience

Ministry of Interior

Data Analyst

Conducted data analysis and created reports using SQL and Excel.
Managed a regional team in implementing a standardized Project Management Office (PMO).
Collaborated with cross-functional teams to develop and implement an employee performance tracking system that increased employee productivity and improved organizational efficiency.
Tools: Python, SQL, MySQL, Excel, PowerBi, PMO.

Mar 2021 - Feb 2023 | Oujda, Morocco

Kaggle

Data Scientist

Achieved Expert rankings in Kaggle competitions.
Successfully competed in various types of competitions.
Utilized unique approaches to solve complex problems.
Participated in both individual and team-based competitions.
Tools: Python, OpenCV, Keras, Tensorflow, PyTorch

Dec 2019 - Present | Remote

UPWORK

Data Scientist | ML

Utilizing clear and concise communication to effectively convey complex data insights to clients.
Demonstrating the ability to manage and execute complex data projects from start to finish
Tools: Python, Scikit-learn, Machine Learning.

June 2015 - Present | Remote

Projects

                
User Satisfaction Flights
                  Flight Satisfaction Analysis using Power BI
                
AccomplishmentsTools: Power Bi, Excel
Flight Satisfaction Analysis: Analyze flight satisfaction using Power BI. Interactive reports explore baggage handling, 
                    check-in service, online booking, and more. Gain insights to enhance customer experience.

Flight EDA
                  Flight Exploratory Data Analysis April 2023
                
AccomplishmentsTools: Python, Data Visualisation 
This project aims to analyze the Exploratory Data Analysis (EDA) of flight data for the month of April 2023. 
                    The dataset provides valuable insights into various aspects of flights, including on-time performance, delays, 
                    airline operations, and other related factors.

Smart Garbage Detector
                  Smart Garbage Detector is a robot that detects garbage.
                
AccomplishmentsTools: MQTT, CNN, Raspberry Pi
The robot is capable of avoiding obstacles.
The CNN model used for image classification was built from scratch, achieving an accuracy of 98%.
The notifications service using MQTT protocol allows the user to receive real-time updates.

DW Financial dataset
                  A data warehouse designed to store and manage sales and financial data.
                
AccomplishmentsTools: SQL, Data Modeling, Talend, QlikView, ETL.
Designed using a dimensional modeling approach, with fact tables and dimension tables.
QlikView is used to access the data warehouse and generate reports and visualizations.

Backdoor Attack
                  A Interactive program that gives access to a system that is executed on.
                
AccomplishmentsTools: Python, Bash.
Command execution.
Access file system.
Upload/download files.
Run keylogger...etc.

Parallel Computing
                  Big data Algorithm and more.
                
AccomplishmentsTools: Big Data, Machine Learning, Web Development.
The most used Big Data Algorithem.
Machien learning applications in Big Data.

PyFed
                  PyFed is a benchmarking framework for federated learning extending PySyft.
                
AccomplishmentsTools: Python, Machine Learning.
PyFed is an open-source and scalable simulation framework of federated settings that supports N-IID data.
The results show that PyFed outperforms existing benchmarks in terms of convergence and accuracy.

 Analysis on Uber Event Data
                  
                  Cluster Analysis to Detect and Visualize Popular Uber Locations
                
AccomplishmentsTools: Spark, Kmeans, Hadoop,SQL
Clusters of Uber data based on the longitude and latitude.
Analyze the cluster centers by date/time, usings Spark SQL.