BRANDON ABUGA

Having completed my final year at Kenyatta University for a Bachelor's in Mathematics and Computer Science and with a strong foundation in both fields, I'm passionate about applying my skills to real-world challenges. In the last 2 years of my academic journey, I have undertaken impactful projects that showcase my abilities in data science. These include creating a personalized movie recommender system employing the surprise module and developing a property sale price prediction model using multiple linear regression. Additionally, my fluency in both written and spoken English, coupled with my familiarity with SQL provides an added advantage, enhancing my capabilities to address business-related queries efficiently.

Leaf disease detection

● Leaf disease classification project for maize, potato, and tomato leaves is done in Jupyter notebook.

● Inception model was employed for effective feature extraction.

● The model was deployed using Streamlit for interactive and user-friendly access.




Movie recommendation system

● Movie recommender system for personalized recommendations based on user's past movie ratings.

● Utilized the Surprise module, specifically employing Singular Value Decomposition (SVD) for modeling.

● The system takes into account a sample user's past movie ratings to generate personalized recommendations.

● The system provides five movie recommendations for each user, enhancing the user experience with a diverse set of suggestions.

● The model was trained and tested on a dataset containing user ratings for movies.




Properties sale price prediction

● Employed multiple linear regression, indicating the consideration of multiple independent variables in predicting the target variable (sale price)

● Used Root Mean Squared Error (RMSE) as the evaluation metric to assess the accuracy of the prediction model.

● Utilized a dataset from Kaggle containing relevant features such as property size, location, number of bedrooms, and other relevant factors influencing property sale prices.