This repository is a showcase of my extensive experience in advanced data analytics, data engineering, machine learning, and the latest trends in Generative AI. It includes a diverse range of projects that I have worked on, including in-depth ETL/ELT, data analysis, computer vision, natural language processing (NLP), and A/B testing. Each project reflects my proficiency in leveraging data to drive actionable insights, optimizing machine learning models, and implementing cutting-edge AI techniques.
AdTech Best Practices
-Data, Algorithms, and Engineering Challenges in Price Floor Optimization in AdTech
Data Engineering
Data Analytics
- Exploring Major Cities Health Indicators
- Airline Tweet Analysis to discover negative opinions of passengers towards service improvement
- Simple Tweeter Data Analysis
- Exploratory Data Analysis for Predicting Eurropean Soccer Data
Natural Language Processing
- Amharic Word Embedding
- Text pre-processing for Amharic
- Augmenting the GRU part-of-speech tagger with sub-words: Amharic Neural Postagger
- PosTagger for Wolaita Language
- Amharic-English Neural Machine Translation
- Deep Learning for Text classification - CNN, RNN, BERT
Transfer Learning for NLP
- [Universal Encoders: ELMO and Google Universal Encoders]
- Fine-tunning with transformers: Text Classification(XLNet, BERT, ROBERTa, XLM)
Classification: Predictive Analysis
- [Mobile Money and Financial Inclusion in Tanzania Challenge]
Regression: Predictive Analysis
- [Flight Delay Prediction Challenge]
- [Fraud Detection in Electricity and Gas Consumption Challenge]
- Working with English Premier League Seasonal Data: Predicting winning team