A restaurant recommendation system to support small Houston businesses during the pandemic won this year’s Rice Datathon, a competition held virtually Feb. 5-6 and presented by Rice University’s Data Science Club and Data to Knowledge (D2K) Lab.
The food4thought team topped 43 projects submitted by 159 final participants in the third annual event. Of 333 students who initially registered, 21% were from outside Rice. The competition awarded $9,000 worth of prizes.
Each team chose a topic from a predetermined list. Team members were provided with related datasets to analyze.
The food4thought team of Rice sophomores Sarah Han, Megan Xiao, Claire Xu and Andy Wang created an online platform that collects a user’s dining preferences and location information and delivers recommendations based on thousands of reviews of Houston restaurants. Each member of the team won $400.
The second-place team, COVID CoughNet, created an algorithm that collects audio and recognizes the differences between COVID-19 coughs and non-COVID coughs, with an estimated accuracy of 90%. The program developed by Rice seniors Will Mundy and Shryans Goyal is not meant to replace testing, but would give users a better sense of their possible infection from home, reducing potential transmission to others. Each student won $200.
Team Titans-Telemedicine Trends won third place for its development of a means to measure the probability that people in a census tract would use telemedicine services. The goal was to help identify underserved areas that could benefit from telemedicine. Each of the team members -- Rice admit Jacob Kasner, senior Franklin Briones, junior Talia Frindell and freshman William Hou of the University of California, Irvine -- won $100. The team also won a category sponsored by 2nd.MD.
Individual category winners included:
- Link, with an algorithm to recommend agencies and vendors for industry, sponsored by Bill.com;
- Hot Dog Sale Prediction, with a model that can forecast sales to avoid food waste due to the miscalculation of demand, sponsored by Chevron;
- Make a Trade, a Bitcoin prediction and business logic program, sponsored by QuantLab;
- Social impact winner Cessation, which used machine learning to find correlations between smoke shops and poverty to propose policies that address tobacco addiction in Houston.
