CV

This is a description of the page. You can modify it in '_pages/cv.md'. You can also change or remove the top pdf download button.

Basics

Name Taissir Boukrouba
Label Data Scientist
Email taissirboukrouba@outlook.com
Github taissirboukrouba
Summary MSc Data Science graduate from the University of Hertfordshire with a BSc in Computer Systems, skilled in data modeling, visualization, and wrangling.

Education

  • 2023.09 - 2024.09

    Hatfield , UK

    Msc Data Science
    University of Hertfordshire
    • Machine Learning & Neural Networks
    • Data Handling & Visualisation
    • Data Mining & Discovery
  • 2019.09 - 2021.09

    Algeria

    Bsc Computer Systems
    University of UHBC
    • Algorithms & Data Structures
    • Statistics
    • Graph theory

Work

  • 2023.07 - 2023.09
    Data Science Intern
    MajestEYE
    • Researched about the company/customer’s domain (banking)
    • Created data dictionary and listed the data model (dimension & fact tables)
    • Enhanced invoice image quality using CNNs
    • Removed stamp and watermarks using openCV and deep learning algorithms
    • Extracted tables and texts from using different OCR methods
    • Used Basic Language models for Named Entity Extraction (NER)
  • 2023.05 - 2023.06
    Applied Data Science Lab Intern
    WQU
    • Created an interactive dashboard for a clustering problem (survey of consumer finances)
    • Performed exploratory data analysis on housing prices in Mexico
    • Predicted earthquakes damages for households in India using decision trees
    • Removed stamp and watermarks using openCV and deep learning algorithms
    • Used Gradient Boosting for the Taiwan bankruptcy data
    • Applied data wrangling using SQL
  • 2023.04 - 2023.05
    Data Science and Business Analytics Intern
    The Sparks Foundation
    • Performed EDA on SampleSuperstore dataset (Retail)
    • Predicted the number of optimum clusters for the Iris dataset
    • Used Linear Regression to predict student score percentage based on study hours
  • 2023.03 - 2023.05
    Big Data Scientist
    Djezzy
    • Explored data dictionary and researched client’s domaine (insurance)
    • Implemented the big dataset into the Apache Spark Environment
    • Solved different data problems (input typos, redundance ..etc) using Scala
    • Introduced Fairness into the data using manual and automated Curations
    • Created Multiple KPIs that explains the company's financial status and performance
    • Deployed the work into a data product as requested by the client (dashboard)
    • Presented the data product to the client

Skills

Techs
Machine Learning Modelling
Natural Language Processing
Data Visualisation
Deep Learning
Data Wrangling
Data Engeneering
Text Classification
Libraries
NumPy
Scikit-learn
Pandas
TensorFlow
Statsmodels
PyTorch
Plotly Express
Seaborn
Matplotlib
Keras
NLTK
spaCy
Languages
Python
R
Scala
SQL
Excel

Languages

English
Fluent
French
Fluent
Arabic
Native