About
I'm a full-time data analyst with a passion for data storytelling, machine learning, building things, and the outdoors! Let's connect and collaborate!
Projects
Every year, the National Highway Traffic Safety Administration (NHTSA) publishes data about fatal car crashes in the United States. My interest with this project was to analyze the data from 2010 to 2020 to determine if a better understanding of the factors that contribute to these accidents can be learned. The data was acquired from NHTSA’s online querying tool and my work was focused on data cleaning, data wrangling and data visualizations.
Used jsonlite, spotifyr, lubridate and plotly packages in R to analyze and visualize personal summary statistics of listening behaviors from January 2022 to October 2022. And, showing the comparison of my results to Spotify's official results.
Found valuable business insights that can explain how consumers are using BellaBeat's smart devices. Insights gained by analyzing user's smart device fitness data.
Side Projects
Custom Token Board is a customizable app to motivate children to learn and complete tasks. It is a visual reward system for children with special needs and children of all ages and abilities. A token economy is a system of behavior modification based on the systematic reinforcement of target behaviors. The reinforcers are symbols or "tokens" that can be exchanged for rewards. Rewards are given after a number of tokens are earned. A token economy is based on the principles of operant conditioning and is used in applied behavior analysis (ABA) with children with autism spectrum disorders.
The app provides the children with visual information about when they can earn their reward using a set number of earned tokens.
While it's currently a work in progress, our team at PAEM are creating a simple and free soundboard app. Uniquely, we want the app to help those who are non-verbal or have a hard time speaking to communicate with any person they need or want to. This is my first time building an iOS app, so we're taking our time to build it. If you have any ideas or want to collaborate, reach out to me :)
Writing
Co-authors: Valentina Colorado, Mohammed Juma, Oguzhan Topsakal, Tahir Cetin Akinci
As machine learning continues to influence our daily lives, it becomes crucial for data scientists to comprehend the reasoning behind their models' predictions. This article aims to assess and analyze the effectiveness of two open-source tools, Alibi and Explainer Dashboard, in providing explainability for different ML algorithms and their outcomes. By doing this, we provide a sample framework for comparison and insights into the capabilities of explainability software. To facilitate a comprehensive evaluation, a benchmark chart was compiled, focusing on three key metrics: satisfaction, trust, and effectiveness.
Work Experience
Education
Certifications
Gained hands-on experience creating dashboards and ETL pipelines with SQL, Google BigQuery, and Tableau. These tools helped me further my knowledge of business reporting, building visualizations, and data modeling.
Gained hands-on experience and practice using Python to solve real data science challenges. Utilized popular libraries such as Pandas, numPy, matplotlib, and SKLearn for modeling, statistics, and storytelling.
Gained hands-on experience with large datasets, SQL queries, R programming, compelling visualizations, and data-driven decisions.