Yonas Moges
Addis Ababa, Ethiopia
Adama Science and Technology University
MSc in Computer Science and Engineering
Email: softeng2006@gmail.com
DE Tools
SQL
ETL
Tableau
Kafka
DBT
Apache Airflow
Azure
Programming
Python
Java
C++
JavaScript
Automation Tools
GitHub Actions
Dockers
DVC, MLflow, CML
Unit testing
ML Tools
Scikit-Learn
Tensrflow
Pytorch
CNN
About me
A Machine Learning Engineer with M.Sc. in Computer Science and Engineering and extensive ML algorithms, Python, Exploratory data analysis, transformation, visualization, feature engineering, and machine learning modeling experience. I am also experienced in creating fault-tolerant distributed and scalable end-to-end ML pipelines.s.
Education
10 Academy (August 2022 - November 2022)
Machine Learning, Data Engineering, and Web3 Engineering Training
Key Courses:
Designing and building data pipelines (ELT and ETL)
Building Machine Models and deployment
MLOps and CI/CD
Dashboard and data visualization
Community building and career thinking
Technical writing and blogging
Adama Science and Technology University (Oct 2016 - May 2019)
M.Sc. in Computer Science and Engineering
Key Courses:
Advanced Machine Learning,
Image Processing,
Big Data,
Algorithm Analysis and Design,
Research Methods, etc
Adama Science and Technology University (Oct 2009- Jun 2014)
B.Sc. In Information Technology
Key Courses:
Applied and Discrete Mathematics,
Probability and Statistics,
Fundamentals and Advanced Programming,
Artificial Intelligence and Expert System,
Data Structure and Algorithm,
Fundamentals and Advanced Database, etc
Work Experience
- Lecturer
Haramaya University(May 2019- 2021)
Courses taught includes;
Fundamentals of Programming, Advanced programming,
Distributed System,
Software Design and Architecture
- System Analysit and Designer
INSA (Jan 2015- Oct 2015)
Prototype Design
Integration Testing
System analysis and Design
Projects
This Telecom-Data-Analysis repo contain .py files which stated about the exploratory data analysis operations in detail on Telecommunication data. this exploratory data analysis shows cleaning, pre-processing, filling missing values and producing clean data that are ready for machine learning. the machine learning algorithm takes the clean data and perform some learning algorithm for producing learning model.
This project aims to forecast sales in all Pharmaceutical stores across several cities six weeks ahead of time. It is identified that factors such as competitor distance, promotions, school and state holidays, seasonality, and locality as necessary for predicting the sales across the various stores. Previously recorded data was provided and future sales prediction is made using that data.