Trader Performance & Bitcoin Market Sentiment Analysis A data science project analyzing trader behavior in relation to Bitcoin market sentiment using real-world trading and sentiment datasets. Includes data cleaning, visualization, and performance insights.

This project aims to develop a machine learning model that predicts whether a customer will churn based on demographic, account, and service-related data. By identifying at-risk customers, businesses can proactively implement retention strategies.

UCL Machine Learning Datasets and Youtube video Tutorials

Sample images of Computer vision YOLO like application

Comprehensive ML analysis of global fire incidents using NASA FIRMS satellite data. Includes data cleaning, EDA, classification, regression, anomaly detection, and visuals. Highlights feature importance and key insights into fire confidence and intensity across different regions.

Here is a compilation of coding challenges I successfully completed during my time at the HyperionDev bootcamp, conducted by the Department for Education (DfE).

In my EDA of the Superstore_USA dataset, I cleaned the data and analyzed profit, customer segments, and sales trends. I identified opportunities to boost profit through better pricing strategies, cost management, and targeted customer segments. Insights from sales patterns and customer behavior will help refine strategies to increase profitability.