Arthur U.

Key Skills

Software

Other

Top Subject Matter

Handwriting recognition / OCR

Predictive modeling / forecasting

Legal Services & Contract Review

Top Data Types

Text

Document

Top Task Types

Text Generation

Freelancer Overview

A.I/Machine Learning Engineer (model development and deployment). Brings 8+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Other. Education includes Bachelor of Science, University of the People (2021) and Certificate, Codecademy (2023). AI-training focus includes data types such as Text and labeling workflows including Text Generation, Evaluation, and Rating.

Labeling Experience

A.I/Machine Learning Engineer (model development and deployment)

OtherTextText Generation

Developed and deployed a machine learning system for handwriting scribble decoding using Python tooling to improve predictive accuracy. The work involved transforming unstructured handwriting inputs into model-ready representations for inference and evaluation. The focus was on applying an ML pipeline to real handwriting data to increase performance metrics by 35%. • Utilized easyOCR for handwriting text extraction • Built and tested a predictive ML model workflow • Collaborated with interdisciplinary teams from ideation to deployment • Improved accuracy by 35% through iterative model development

2024 - 2025

Data science Intern (modeling and dataset preparation)

OtherText

Engineered predictive models using Python libraries to support forecasting of antimalarial drug needs and electricity demand/supply gaps. The work required preparing data with preprocessing and ensemble learning methods to produce validated forecasting outcomes across multiple datasets. Although not described as manual annotation, the role involved constructing training-ready datasets and measuring predictive performance to drive model accuracy improvements. • Pre-processed datasets using Python and ensemble learning • Improved forecasting accuracy by 15% via optimization and validation • Achieved 85% accuracy in electricity demand/supply forecasting outcomes • Built predictive modeling pipelines in scikit-learn, NumPy, and pandas

2024 - 2024

Education

Work History