Welcome to my data analysis portfolio! I’m Marlene Prado, a data analyst and engineer with a passion for transforming data into actionable insights. With a background in IT, data engineering, and cybersecurity, I leverage my skills to solve complex problems and drive decision-making. My expertise includes data visualization, statistical analysis, and machine learning.
- Overview: This project analyzes bike sales data, focusing on customer demographics, commuting habits, and purchasing behaviors. The analysis was done using Google Sheets to clean and organize the data, create visualizations, and build an interactive dashboard.
- Tools Used: Google sheets, Pivot tables and Dashboards
- Key Insights: The dashboard allows stakeholders to quickly filter and analyze bike sales trends based on gender, age group, and marital status. This visualization improves decision-making for marketing and sales strategies.
- Link to Code/Demo: GitHub Repository.
- Overview: This project analyzes Kickstarter campaign data, focusing on campaign success rates, backers, and funding patterns. The analysis involved cleaning and transforming the data, creating new columns, and building visualizations using pivot tables and histograms to uncover insights about successful campaigns.
- Tools Used: Google Sheets, Pivot Tables, Histograms, Data Transformation
- Key Insights: The analysis includes a distribution of success rates based on campaign length, success rate by pledge goal range, top-performing categories by success rate, backers versus category trends, and insights into the best time and day to launch a campaign. These visualizations provide valuable data-driven recommendations for optimizing Kickstarter campaigns.
- Link to Code/Demo: GitHub Repository
- Overview: This project analyzes global video game sales data from Kaggle, focusing on sales trends over time, by genre, and by platform. Using Tableau, I visualized key insights into the performance of different game genres and platforms across years.
- Tools: Tableau, Kaggle (CSV data), Data Visualization Techniques
- Key Insights: The project visualized global sales trends over time, with genres color-coded for easy comparison. Filters were applied to analyze sales for specific platforms, such as PlayStation 1-4, and genre-wise sales comparisons revealed the top-performing genres across different years. These visualizations were then combined into an interactive dashboard, allowing for dynamic exploration of sales data by year, genre, and platform.
- Link to Code/Demo:GitHub Repository
- Overview: In this project, I created bins for year ranges in the video game sales dataset to analyze sales trends over time. The focus was on categorizing years, performing quick table calculations for percent of total global sales, and comparing global sales with EU sales.
- Tools: Tableau, Data Binning, Calculations (Percent of Total, Custom Calculations)
- Key Insights: Year ranges were grouped into 5-year bins, transforming the numeric Year field into a categorical field. Excluded null data to focus on sales from 1990 to 2015. Created a quick table calculation to display the percentage of total global sales. Built custom calculations to compare global sales with EU sales, showcasing the difference between the two.
- Link to Code/Demo:GitHub Repository
-
Overview: This project demonstrates the use of joins in Tableau by combining multiple tables (Demographics, Job Title, and Salary) from an Excel file. The project focuses on understanding different types of joins—Inner, Left, Right, and Full Outer—and their impact on the dataset, mimicking SQL-like joins in Tableau to analyze employee demographics and salary data.
-
Tools Used: Tableau, Excel
-
Key Insights:
- Explored different join types (Inner, Left, Right, and Full Outer) using the
EmployeeIDfield. - Analyzed how different joins affect the resulting dataset, such as matching records and missing data.
- Joined tables to consolidate employee demographics, job titles, and salaries into a single view.
- Visualized the total salary per employee by creating a simple bar chart with
Employee Nameon columns andSum of Employee Salaryon rows, using colors to differentiate salary totals.
- Explored different join types (Inner, Left, Right, and Full Outer) using the
-
Link to Code/Demo: GitHub Repository
-
Overview: This project analyzes Airbnb listings in Seattle using data from 2016. The dataset includes listings, reviews, and calendar data. I performed several joins and created visualizations in Tableau to explore pricing, location, and trends that impact Airbnb profitability.
-
Tools Used: Tableau, Excel (Airbnb Dataset)
-
Key Insights:
- Price by Zipcode: Analyzed the average price of Airbnb listings by zipcode to identify the most expensive areas. This helps determine where to buy property for Airbnb rentals.
- Price per Zipcode Map: Created a map visualization showing average prices for each zipcode, colored and labeled to highlight areas with the highest rental prices.
- Revenue per Year: Analyzed Airbnb revenue trends over the weeks of 2016 to determine the best time to list properties.
- Average Price per Bedroom: Examined how the number of bedrooms affects price, showing that one-bedroom properties are performing well.
- Distinct Count of Bedroom Listings: Filtered out null and zero-bedroom listings and counted distinct bedroom listings to assess property availability by size.
-
Visualizations:
- Price by Zipcode: A bar chart showing average Airbnb prices across Seattle’s zip codes.
- Price per Zipcode Map: A map view of Seattle with zip codes colored by average price, helping to identify the most lucrative areas for Airbnb.
- Revenue per Year: A line chart of revenue trends across weeks in 2016, helping identify the best times to list properties.
- Average Price per Bedroom: A bar chart displaying average Airbnb prices based on the number of bedrooms.
- Distinct Count of Bedroom Listings: A count of Airbnb listings by the number of bedrooms.
-
Link to Code/Demo: GitHub Repository
-
Overview: This project analyzes the Tech Moms Application Data to uncover key insights into the demographics of applicants for the Tech Moms program. The goal was to identify trends in employment status, education levels, household income, and diversity within the applicant pool. Tableau was used to create visualizations and generate insights based on the provided dataset.
-
Tools Used: Tableau, Google Sheets, CSV
-
Key Insights:
- Employment Trends: 30% of the students are unemployed, indicating a potential need for career development and skill-building opportunities.
- Income Distribution: The income levels of the students were spread across various brackets, with a significant portion in the lower-income ranges, indicating a need for career upskilling.
- Education Levels: A large proportion of the students hold High School / Some College, indicating that many are seeking to further their education or upskill for better career opportunities..
- Diversity: The dataset highlighted a majority of students identifying as White, while 37.23% of applicants identify as BIPOC+ (Black, Indigenous, People of Color, and other minorities), showcasing a relatively diverse group applying to the program.
-
Link to Code/Demo: GitHub Repository: GitHub Repository
-
Overview: This project analyzes the Tech Moms Application Data to uncover key insights into the demographics of applicants for the Tech Moms program. The goal was to identify trends in employment status, education levels, household income, and diversity within the applicant pool. Power BI was used to create visualizations and generate insights based on the provided dataset.
-
Tools Used: Power BI, Google Sheets, CSV
-
Key Insights:
- Employment Trends: 30% of the students are unemployed, indicating a potential need for career development and skill-building opportunities.
- Income Distribution: The income levels of the students were spread across various brackets, with a significant portion in the lower-income ranges, indicating a need for career upskilling.
- Education Levels: A large proportion of the students hold High School / Some College, indicating that many are seeking to further their education or upskill for better career opportunities.
- Diversity: The dataset highlighted a majority of students identifying as White, while 37.23% of applicants identify as BIPOC+ (Black, Indigenous, People of Color, and other minorities), showcasing a relatively diverse group applying to the program.
-
Link to Code/Demo: GitHub Repository
- Overview:
- Link to Code/Demo: Github Repository
- Technical Skills:
- Data Visualization: Tableau, Power BI
- Data Analysis: Python (Pandas, NumPy), R
- Database Management: SQL, NoSQL
- Machine Learning: Scikit-learn, TensorFlow
- Cloud Platforms: AWS, Google Cloud
- Soft Skills:
- Problem-Solving
- Communication
- Project Management
- Data Analytics and Warehousing: Certification Details
- Data Science Specialization: Coursera
- Machine Learning: Machine Learning Academy
- Email: [email protected]
- LinkedIn: LinkedIn Profile
- GitHub: GitHub Profile