Data Analytics Portfolio

About Me

Hey, I’m Nirav! I am a recent Sports Technology (BEng) graduate from Loughborough University, UK, with proficiency in predictive modeling, data collection, analysis, and visualization using Python, R, SQL, Power BI, Excel, and Cloud Platforms. I’m passionate about uncovering the story within data (because numbers have feelings too!) and presenting insights in impactful ways.

This repository serves as a platform to showcase my skills and share my projects, as well as to track my progress in Data Analytics and Data Science-related topics.

• Click Here! to see my resume.

• Click Here! to view my Github repository with detailed explanations of all my projects.

Project Overviews

Note: Click each project title to view the full project, including code, visualizations, and/or detailed explanations of my analysis steps.

Project 1: Spotify Top Tracks Dashboard (Power BI)

This interactive Power BI dashboard analyzes the most streamed tracks on Spotify from 2018 to 2023, providing a detailed breakdown of streaming trends, artist performance, and song characteristics over time. The project leverages a dataset enriched with Spotify cover art images using the Spotify API and Python, integrating HTML visuals and DENEB-based custom visualizations to create a dynamic and insightful user experience.

Highlights include:

• Track Insights: Key metrics such as total streams, top tracks, and artist performance trends.
• Trend Analysis: Yearly streaming averages and growth rates compared against historical data.
• Track Release Heatmap: A custom DENEB visualization that shows how many tracks were released on specific days and months, offering insights into music release patterns over the years.
• Track Attributes: Analysis of song characteristics like energy, danceability, and valence, presented through intuitive visuals, including a circular gauge for attribute percentages.
• User Engagement: Interactivity features like filters for years, artists, and track selection to explore streaming patterns and insights dynamically.

Click the video below to see a preview of the dashboard in action!

Project 2: UK Road Accident Dashboard (Power BI)

This interactive Power BI dashboard provides a comprehensive analysis of road accidents in the UK for the years 2021 and 2022. Key metrics such as total casualties, accident trends, and breakdowns by vehicle type, road type, and environmental conditions are visualized to uncover meaningful insights.

Highlights include:

• Casualty Overview: Total casualties, serious injuries, and fatalities with year-on-year changes.
• Trends and Distribution: Monthly casualty trends and analysis of urban vs. rural accident patterns.
• Accident Context: Insights into conditions like road type and light conditions that contribute to accidents. This analysis aims to support road safety initiatives and identify areas for improvement in traffic management.

Click the video below to see a preview of the dashboard in action!

Project 3: Data Job Market Analysis

This project was created out of a desire to navigate and understand the job market more effectively as well as to aid me in my job search. It delves into top-paying and in-demand skills to help find optimal job opportunities for data analysts.

Below are the main questions I answer in the project:

• What are the most in-demand skills for the top 3 most popular data roles?
• How are in-demand skills trending for Data Analysts?
• How well do jobs and skills pay for Data Analysts?
• What are the optimal skills for data analysts to learn?

Project 4: Wheelchair Basketball Kinematics App

This project, completed as part of my undergraduate final-year research, involved designing an accessible, cost-effective sensor-based system specifically for wheelchair basketball athletes to monitor performance metrics relevant to their sport. I developed an accompanying R Shiny app that processes data from the system to calculate, display, and analyze key kinematic metrics. This enables athletes to track their performance, pinpoint areas for improvement, and tailor their training programs accordingly. The app serves as a practical tool for athletes to enhance training precision and achieve targeted performance goals.

This project required skills in sensor integration for accurate data capture, data preprocessing to clean and prepare raw sensor data, statistical analysis to derive meaningful insights, and data visualization for an intuitive display of performance metrics. Additionally, it involved R programming for app development, Shiny framework expertise for interactive data visualization, and UI/UX design to create a user-friendly interface.

Supporting Docs: Poster, Report, App

Click the video below to see a preview of the app in action!

Close-up of the designed sensor system attached to the wheelchair: