Bettering Hedging Through Clustering and Stock Selection sponsored by Belvedere Trading
By clustering representative stocks and selecting representative stocks for each cluster, we can substantially reduce the number of stocks required to mirror the movement of given market sectors, making hedging more efficient. This project tackles clustering methods, cluster count estimation, and similarity measurement, among other factors, to build a time series clustering and selection technique well suited to the peculiarities of stock-market data.
Customer acquisition and user experience are key metrics for startups, companies and financial institutions. Data science allows businesses to gain insights from user interactive data, such as unstructured texts from customer service chats and surveys. Two of the Data to Knowledge Lab’s Spring 2021 Capstone teams aim to help businesses gain these insights and ultimately improve customer experience.
Data Science Meet Emotion: Increasing Empathy in Customer Service Interactions Using Natural Language Processing
This project aims to build a model which predicts a real-time probability that a customer will have a positive experience during live customer support chats. To achieve that, five Rice students named the CS Chats team performed sentiment analysis and topic modeling with the data sets provided by D2K Affiliate member Bill.com.
The Bill.com Positive Feedback Cycle: Using Customer Feedback to Understand User Pain Points.
The goal of the customer feedback project is to build data science tools to help the product management team at Bill.com understand what types of users like and dislike the product.
Connecting the dots: How the entire financial world is connected
Team Members: Ye Chen, Seth Kimmel, Ankit Narasimhan, Jordan Pflum, Yifan Zhang
Building upon previous work done to model inter-relatedness of future contracts, we seek to understand market conditions under which such inter-relatedness occurs. This gives us insight into how the futures market operates and allows us to build powerful price prediction models using this knowledge.
Sponsor: Belvedere Trading LLC
Sponsor Mentor: Dr. Andrew Wendorff
D2K Fellow: Weilie Nie
Faculty Mentor: Dr. Dan Kowal
Project Title: Danceable Regression
Project Description: Our project looks at a Spotify datasets from 1921-2021 with features including danceability and acousticness. We explored several outliers in this dataset and used these Spotify-defined features to answer questions about song popularity and genre makeup.
• Natalie Goddard (Materials Science and Nanoengineering ‘21)
• Nathan McCoslin (Political Science, Asian Studies ‘22)
• Franco Gomez (Mathematical Economic Analysis ‘24)
• Andrei Mitrofan (Bioengineering ‘23)
• Hanna Gratch (Sociology ‘21)
Project Title: Airbnb: Host Classification and Price Prediction
Project Description: Our project seeks to optimize the experience of Airbnb hosts in order to allow them to price their listings most appropriately to maximize earnings. We have conducted data analysis of Austin, TX Airbnb listings in order to explore the differences in host classifications and the characteristics that most impact an Airbnb listing's price.
• Alana Pickens (Economics ‘23)
• Franklin Briones (Bioengineering, ‘21)
• Max Boekelmann (Sport Management ‘21)
• Daniel Cufino (Computer Science ‘24)
• Archit Chabbi (Bioengineering ‘24)
Cross-Community Comparison of Fire and Emergency Medical Services
Team Members: Toby Han, Sue Kim, Augi Liebster, Matthew Mutammara, Chris Yum
Our work aims to organize fire departments into cohorts based on demographic/incident factors via statistical clustering methods. This context will allow departments to compare how well they provide services to their communities and explore ways that similar departments have improved their operations and outcomes.
Sponsor Mentor: Brian Collins, Molly Hausmann, Jason Posthuma, Amy Ehm
D2K Fellow: Daniel Bourgeois
Interested in working with Rice students and faculty on a real-world data science project? Send us an email at email@example.com.