- 🌱 At Epython Lab, I specialize in providing Data Engineering, Data Science, and Web Development solutions.
- 💼 I am passionate about analyzing datasets, uncovering insights, and developing strategies to help businesses grow.
- 🚀 I have expertise in Python, SQL, Flask, Streamlit, Power BI, Tableau, and Teaching.
- 📚 I am committed to continuous learning and innovation, expanding our capabilities in machine learning, data visualization, and web technologies.
| Programming Languages & Frameworks | Data Visualization & Analytics | Cloud & DevOps | Web Development | IDEs & Editors |
|---|---|---|---|---|
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
|
 |
 |
 |
|
Description: A machine learning model developed to predict credit risk and assign credit scores, supporting data-driven lending decisions for Bati Bank's Buy-Now-Pay-Later (BNPL) service in collaboration with an e-commerce platform.
Tools Used: Python, Flask, Sklearn, Visualization Tools
Key Features:
- Exploratory Analysis
- RFM Model Development(Customer Risk Classification)
- Machine Learn Model(Predicting Customer Risk)
- Report
Description: A comprehensive data warehouse solution for Ethiopian medical business data scraped from Telegram channels, including data scraping, object detection with YOLO, and ETL/ELT processes.
Tools Used: Python, Flask, Sklearn, Visualization Tools, dbt(Data Build Tool), PostgreSQL, Telegram API
Key Features
-
Scraping data from telegram channels(text, images)
-
Cleaning and storing into PostgreSQL
-
ETL using DBT
-
Object detection using YoloVx
-
Deployment: API service for real-time object detection, ETL, and predictions via Flask, Database, and YoloVx.
Description: Building a real-time data ingestion and entity extraction pipeline for Amharic messages from Ethiopian e-commerce Telegram channels. The system leverages fine-tuned Large Language Models (LLMs) to identify key business entities such as product names, prices, and locations. The extracted information is used to populate a centralized platform for EthioMart to streamline e-commerce activities in Ethiopia by consolidating decentralized Telegram channels into a unified hub. The project also includes handling Amharic-specific linguistic features and evaluating model performance for Named Entity Recognition (NER).
Tools Used: Python, Flask, Sklearn, Visualization Tools, Deep Learning
Key Features:
- Extract Amharic Telegram Messages(E-commerce channels)
- Labeling the extracted messages(NER)
- Train the model using Deep Learning(LLM)
- Report)
Description: This project mainly focused on the GitHub Search Tool, which provides enhanced search functionality and allows users to find repositories based on topics, ratings, and programming languages.
Tools Used: Python, Flask. Key Features:
- Search top-rated GitHub repo
- Search by programming
- Search by Topic
Check more projects at Epython Lab. I am always open to new opportunities and partnerships. Contact me for collaboration, consulting, or any data-driven project needs!