Welcome to my project page! I'm Biniam, an experienced Bioinformatics professional with over 5 years of industry experience. My passion is using data to drive sustainable decision-making and positively impact the world. I specialize in utilizing technologies such as Machine Learning, Python, R, SQL, Tableau, and Linux. I am excited to share my work with you and look forward to collaborating on projects that make a real difference.
LinkedIn: Biniam Feleke
In this project, we will use GoalZone Fitness club's dataset to build and evaluate classification ML models (Logistic Regression and XGBoost) in Python. The best model will be recommended to GoalZone Fitness Center to predict gym member attendance. This will help determine whether the gym should make another space available or not.
Using audio music data, we will be building machine learning models to predict music genres (Hip-Hop or Rock). The classification ML models include Logistic Regression, Decision Tree and XGBoost. The best model will be chosen based on a chosen performance metric.
We will using Python to explore the GitHub history of the Scala language to figure out who has had the most influence on its development and who are the experts.
In this project, we analyze the investment potential and risk of Amazon and Facebook using the Sharpe Ratio and pandas. The Sharpe Ratio, a metric developed by Nobel Prize winner William Sharpe, compares the return of an investment to an alternative while considering its risk (measured by standard deviation of returns). Real financial data is used in the project for analysis.
This project will use the Python image library Pillow to manipulate bee images, then build a machine learning model to identify bee species. The goal is to enhance field data collection by quickly and accurately distinguishing between honey bees and bumble bees. Deep learning techniques will also be leveraged to further improve the model's accuracy.
In this project, we will explore the impact of handwashing on patient outcomes at two maternal clinics. Using statistical analysis and machine learning in Python, we will analyze the available data and determine the significance of handwashing on patient health outcomes. The goal is to provide insights and recommendations for improving maternal health care.
In this project, we aim to build and evaluate a robust XGBoost regression model using the Iowa housing dataset. Our goal is to identify the top 20 influential features that have the greatest impact on the house price, and use these features to make predictions. The process will be implemented in Python.