Summary
Overview
Work History
Education
Skills
Work Availability
Quote
Timeline
Generic

Pablo Simon Nguema Obiang

Summary

Accomplished Data Scientist/Machine Learning Engineer with a proven track record of over 2 years in the field of data science and development. I possess a strong command of statistical modeling, statistical hypothesis testing, and optimization methodologies, consistently delivering impactful solutions. Proficient in AI, machine learning, and data science, I am well-versed in utilizing Python with Scikit-learn, TensorFlow, Keras, and SQL languages to drive data-driven insights and innovation.

Overview

2
2
years of professional experience

Work History

Junior Data Scientist

Caterpillar Inc.
Chillicothe, IL
08.2022 - Current
  • Contributed as a member of an esteemed MLOps team entrusted with constructing robust ETL pipelines to support the mechanical engineering team in proactively mitigating future engine problems.
  • Conducted data mining from a Snowflake database, utilizing SQL queries to extract relevant information for analysis and further processing.
  • Performed comprehensive data analysis and labeling using rule-based algorithms, implemented in Python, to address short-term cases.
  • Utilized an array of advanced statistical modeling and machine learning techniques, including KNN, Naive Bayes, Random Forest, and others, to develop robust automated prediction models. The primary focus was on achieving a minimum precision level of 90%.
  • Orchestrated the deployment of solutions through an Internal Server Software, seamlessly integrated with the Azure environment, ensuring efficient and scalable implementation.

Junior Data Scientist

Enhance It
Atlanta, GA
01.2022 - 08.2022
  • Collaborated with a DevOps team to establish a robust pipeline for automating data entry of scanned government forms, leveraging AWS as a storage solution and AWS Redshift as our database platform.
  • Implemented page classification through advanced image classification techniques using Python, TensorFlow-Keras, and Convolutional Neural Networks (CNN), achieving an impressive accuracy rate of 98% and a precision rate of 100% for the targeted pages.
  • Employed OpenCV for precise homography to enable seamless image cropping for Optical Character Recognition (OCR), successfully achieving accurate OCR results in 99% of cases.
  • Utilized AWS text Extract for OCR, effectively extracting relevant information from images and securely storing them in our AWS Redshift Database.
  • Applied Natural Language Processing (NLP) techniques, including named entity recognition and fuzzy matching, to enhance context-based information extraction

Junior Machine Learning Engineer/Data Scientist

Mobile Apps
Marietta, GA
05.2021 - 01.2022
  • Served as a Data Scientist/Computer Vision Researcher, dedicated to developing cutting-edge solutions for real-time inference in classifying crushable and uncrushable materials in the company's production pipeline.
  • Utilized OpenCV to optimize image processing efficiency, resulting in an impressive average reduction of image processing time by 70%.
  • Conducted comprehensive evaluations of various computer vision architectures, including VGG16, ResNet, Inception, and EfficientNet. After rigorous analysis, determined ResNet as the most optimal choice, delivering outstanding performance with a recall of 0.85, precision of 0.7, and rapid inference time of approximately 3 seconds.

Education

Bachelor of Science - Electrical And Computer Engineering

Texas Southern University
Houston, TX
05.2021

Skills

  • Critical Thinking
  • Data Management
  • Strong Communication
  • Agile Methodology
  • Database Management
  • Data Mining
  • Database Programming and SQL
  • Python
  • Statistical Analysis(Data Analysis and Business Analysis)
  • Time-Series Analysis
  • Data Visualization
  • NumPy Stack( NumPy, SciPy, Pandas, and Matplotlib)
  • Machine Learning
  • Predictive Modeling
  • Computer Vision
  • NLP
  • Experience with third-party cloud resources (AWS and Azure)
  • Spanish(Native)
  • French(Professional)

Work Availability

monday
tuesday
wednesday
thursday
friday
saturday
sunday
morning
afternoon
evening
swipe to browse

Quote

Reality is nothing but a collective hunch.
Lily Tomlin and Jane Wagner

Timeline

Junior Data Scientist

Caterpillar Inc.
08.2022 - Current

Junior Data Scientist

Enhance It
01.2022 - 08.2022

Junior Machine Learning Engineer/Data Scientist

Mobile Apps
05.2021 - 01.2022

Bachelor of Science - Electrical And Computer Engineering

Texas Southern University

Similar Profiles

CREATE PROFILE
Pablo Simon Nguema Obiang