Hello there! I am a machine learning engineer with a Master's degree in Artificial Intelligence. I possess a deep interest in the field of machine learning and have a strong background in data engineering. My skill set encompasses a wide range of areas such as machine learning, application development, data warehousing, ETL development, and data quality assessment.
I have worked on a number of Machine Learning projects including classification and regression tasks. My projects include sentiment analysis, customer churn prediction, stock price prediction, epitope prediction, spam detection and more. Please take a look at my GitHub repo GitHub repo.
I have extensive experience in various Data Engineering and Management projects involving crucial tasks such as ETL (Extract, Transform, Load) processes, Data Quality Assessment, as well as Metadata Management across diverse domains. Please take a look at my CV to know more.
During my experience in data engineering projects, I have successfully utilized Power BI to create impactful data visualizations and generate comprehensive reports. Additionally, I have employed Python-based visualization techniques in the context of my machine learning projects.
Here's some of my recent Machine Leanring Projects that I have worked on.
I have worked on sentiment analysis projects specific to the English Premier League (EPL) and Formula 1 (F1), analyzing and understanding the emotional and subjective opinions expressed in relation to these sports.
I developed an ARIMA model to forecast Netflix stock prices for the 30 days using historical data. The model determined optimal parameters for predictions, and visualized future trends based on historical patterns.
I have developed a Naive Bayes-based email spam detection model that demonstrates strong performance in distinguishing between spam and non-spam emails, offering an effective solution for email security.
I have performed a data mining exercise on water data and developed an XGBoost model for predicting faulty water pipes. This model can serve as an invaluable tool for proactive maintenance and resource allocation.
I have developed a bank customer churn prediction model testing multiple ML algorithms. The model has strong ability to distinguish between churn and non-churn cases and can help reduce customer loss.
I have developed a credit card fraud prevention system using both machine learning and deep learning techniques. The project aims to create accurate models for detecting fraudulent credit card transactions.