Hamza Murshad

<p>This was a collaborative data analytics hackathon project completed as part of the Code Institute’s Data Analytics with AI program.</p><p>Our team was tasked with exploring a healthcare insurance-related dataset and presenting insights through a clear, interactive dashboard.</p><p></p><p>The project focused on analysing healthcare factors such as BMI and Age to find the greatest cause of healthcare insurance cost, identifying key trends, and investigating relationships between them.</p><p></p><p>Working collaboratively in a team environment, I contributed to:</p><p></p><p>Cleaning and organizing the dataset using Pandas and NumPy</p><p>Conducting exploratory data analysis (EDA) to uncover trends and correlations</p><p>Creating data visualizations in Matplotlib and Seaborn to communicate findings effectively</p><p>Building a Power BI dashboard to present results interactively</p><p>Using GitHub Projects (Kanban board) and branch management in VS Code for workflow coordination</p><p>Presenting findings and data insights to students of Code Institute and our facilitator</p><p></p><p>The hackathon experience helped me strengthen not only my technical skills but also my team collaboration, version control, and project communication abilities which resembled a real-world data analytics environment.</p>

<p>This collaborative data analytics hackathon project explored a dataset from The Movie Database (TMDb) to uncover insights into film trends, audience preferences, and revenue drivers within the movie industry.</p><p></p><p>Our goal was to analyse relationships between movie attributes such as budget, revenue, genres, and ratings to determine what factors most influence a film’s success. The project combined data cleaning, visual storytelling, and dashboard creation to communicate actionable insights.</p><p></p><p>As part of a team, I contributed to:</p><p></p><p>Cleaning and preprocessing the TMDb dataset using Pandas and NumPy</p><p></p><p>Conducting exploratory data analysis (EDA) to identify correlations between variables like budget, revenue, popularity, and runtime</p><p>Creating visualisations in Matplotlib and Seaborn to highlight key insights</p><p>Designing an interactive Power BI dashboard summarizing top-grossing genres, rating distributions, and release trends over time</p><p>Collaborating through GitHub Projects (Kanban) for workflow management and Git branching for efficient version control</p><p>Presenting findings as part of a group presentation simulating a professional data team environment</p>

<p>Electronic Sales is a data analytics project that explores the factors influencing customer behaviour and sales performance in an electronics retail dataset. The dataset (sourced from Kaggle) contains ~20,000 records and 16 features (e.g. customer demographics, product category, loyalty status, payment method). </p><p></p><p></p><p>The goal was to uncover trends and validate hypotheses around loyalty programs, spending patterns, product categories, seasonal sales, and customer segmentation. I cleaned the data, tested hypotheses using visualisations, built interactive charts, and provided business-facing insights.</p><p></p><p>I also documented my entire workflow using Jupyter Notebooks.</p>