Welcome to Darden's Data Scientist Day!

Please make sure to register for the event here if you haven’t done so already.

Thank you for joining us as we celebrate the graduation of our Darden cohort! We’re so proud of all that they have achieved over the last 6 months. Since beginning their journeys into data science on July 13th, they’ve gained hands-on experience in Applied Statistics, SQL, Python, Pandas, Matplotlib, Machine Learning, Natural Language Processing, Data Storytelling, Git, Jupyter Notebooks, Tableau and Seaborn. They put all of these skills to use to develop their capstone –an end to end data science project with actionable insights. As you watch, you can learn more about each grad by clicking their name to visit their Alumni Portal profile.

The event will start promptly at 2:30pm below! If the video doesn’t auto-play for you, please click the play button.

Teams

SpotiScry

Our team analyzed thousands of hip-hop songs from Spotify to determine what features create a top hit. Using insights from both data exploration and modeling, we found several drivers of song popularity. We then made recommendations for musical composition that artists, producers, or anyone in the music industry could use to make their own hit.

AI Learning Team

In light of COVID-19, online learning has become a vital tool for education, and Riiid is a leading provider of AI online educational platforms. Our project focuses specifically on Riiid’s English competency app, which prepares Korean students for the Test of English for International Communication (TOEIC). The goal of our project is to increase the effectiveness of Riiid’s app. We pursued this goal by exploring the data of 100,000 students from Riiid’s database and developing a model that can predict student performance.

 

A Tale of Two Cities

This project evaluates the effectiveness of utilizing the CDC’s Social Vulnerability Index (SVI) as a tool to predict COVID cases in San Antonio and Dallas, Texas. Understanding if SVI accurately predicts pandemic impact is critical for ensuring that vulnerable populations do not miss out on critical resources. Features from this measure will be incorporated into a predictive model that can be used to aid officials in targeting resources to vulnerable communities.

Default Detection Team

The Chinese credit card market is booming, but many citizens themselves are super savers. Who then, should credit card companies target in China? To do this, we need to discover and predict who is likely to default on credit debit or not. Using demographic data and payment history, we developed a model that predicts credit card default six months in the future.

Fourth and Four

Our goal is to measure defensive performances by a player and team that prevent a successful pass completion during the 2018 regular season. To accomplish this task, we will use player tracking data for all drop-back pass plays to identify which coverage options and positions tend to be better performing.