In the D2K Capstone program, interdisciplinary teams of students (advanced undergrads, professional master's students, and Ph.D.) work on a semester-long real-world project sponsored by our D2K Affiliate Members.
Project Title: Down with Duplicates! Identifying Identical Vendors within Bill.com’s Business Network 
- Project Description: We create a machine learning model that takes in vendor data, including vendor’s transactions data, the type of industry the vendor participates in and the words from the vendor’s invoices,
to identify sets of vendors that are likely the same entity.
- Team Members: "Bill.com"
- Davyd Fridman (BS, Computer Science, 2023)
- Xinyue Pang (MS, Data Science, 2023)
- Jiaxin Li(MS, Data Science, 2023)
- ZiZhong Yan(MS, Data Science, 2023)
- Keyan Zhang(MS, Data Science, 2023)
- Ziwei Li (MS, Data Science, 2023)
- Sponsor Mentor: Michael Price (Machine Learning Engineer), Ricardo Fernandez (Senior Machine Learning Engineer)
- D2K Fellow Mentor: Henry Lai (PhD student)
- Rice Faculty Mentor: Prof. Arko Barman
Project Title: Battery Replacement Prediction Based on Survival Analysis 
- Project Description: LivaNova, a medical device company, has created a battery-powered, implantable device used to treat drug-resistant epilepsy. By leveraging survival analysis, we predict the number of
battery replacements needed per year for the next ten years, so patients can continue to receive their
treatment and maintain their quality of life.
- Team Members: "LivaNova"
- Hsing-Yng (Winnie) Louh (Class of 2023 - B.A. Statistics, Minor in Data Science)
- Catherine Yeh (Class of 2023 - B.A. Statistics, Minor in Data Science)
- Siyi (Cici) Du (Class of 2023 - B.S. Statistics, B.A. Cognitive Science, Minor in Data Science)
- Chaoqi Ye (Master of Data Science, 2022)
- Vania (Fanling) Ding (Class of 2023 - B.A. Statistics, B.A. Mathematical Economic Analysis, Minor in Data Science)
- Sponsor Mentor: Andrew Briggs (Director), Megan Christy (Data Scientist), Cheyenne Ehman (Data Scientist), Kayla Frisoli (Data Scientist, Senior Manager), Lauren Nardacci (Senior Manager of Competitive Intelligence), Andrew Zilbauer (Competitive Intelligence and Data Analytics Analyst)
- D2K Fellow Mentor: Raul Garcia (PhD student)
- Rice Faculty Mentor: Prof. Xinjie Lan
Project Title: Westlake Green Connex Recycle Vision 
- Project Description: To upgrade the waste reuse chain, Westlake partnered with our group to provide Westlake with a solution to the problem of reducing the labor costs associated with processing poor quality scrap material. For achieving this objective, our team is creating a user interface that can automatically
identify scrap quality levels from images uploaded by scrap sellers. In doing so, DIMEX would be able to know material attributes prior to collection which would greatly improve their data acquisition process and optimize profits.
- Team Members: "AI Recycling Vision"
- Tona Akerele (MS Data Science, 2023)
- Atanu Dahari (MS Computer Science, 2022)
- Zack Shang (MS Electrical and Computer Engineering, 2022)
- Jingyi Wang (MS Data Science, 2022)
- Sponsor Mentor: Michael Dessauer (Manager of Data Science), Chris Lynn Director (Technical Services), Nathan Arden
- D2K Fellow Mentor: Dr. Jyotikrishna Dass (Research Scientist, D2K)
- Rice Faculty Mentor: Prof. Xinjie Lan
Project Title: Greater Houston Equity Analysis 
- Project Description: Every year, BakerRipley works with communities in the Greater Houston area by providing resources and connections to further their growth. We developed a Social Vulnerability Index dashboard to map inequities of neighborhoods in Harris County and identify areas for BakerRipley to develop new programs.
- Team Members: "BakerRipley"
- Kathy Wang (2022, Master of Computer Science)
- Jenny Bechtold (2023, Statistics)
- Aditi Narwaney (2023, Statistics)
- Parker Beck (2023, Computer Science)
- Sponsor Mentor: Dr. Kristen Deppe (Director of Research & Evaluation), Travis Harry (Data Visualization & Insights Specialist), Nelly Beugre (Data Automation & Evaluation Specialist)
- D2K Fellow Mentor: Xin Tan (PhD student)
- Rice Faculty Mentor: Prof. Xinjie Lan
Project Title: Cardiac Output Prediction on Pediatric Patients Using Non-invasive Measurements 
- Project Description: Cardiac output is the measure of how much blood the heart is pumping and it can only be measured accurately through invasive means. However, for pediatric patients, the technological and physiological limitations of traditional methods make cardiac output measurement unviable, requiring us to apply our creativity, ingenuity, and our knowledge of data science to predict cardiac output through non-invasive measurements.
- Team Members: "The IronHearts"
- Elian Ahmar (2023 Computer Science, Data Science)
- Yaofeng Xie (PhD, Physics)
- Andrei Mitrofan (2023 Bioengineering)
- Haoxi Kuang (Grad Data Science)
- Ekrem Kizilkaya (2023 Computer Science, Statistics)
- Sydney Le (Grad. Computer Science)
- Sponsor Mentor: Sulimon Sattari (Researcher, Medical Informatics Corp.)
- D2K Fellow Mentor: Maryam Khalid (PhD student)
- Rice Faculty Mentor: Prof. Arko Barman
Project Title: Understanding Contributing Factors to Motor Vehicle Incidents in the Houston Fire Department 
- Project Description: The operation of Houston Fire Department (HFD) vehicles presents a safety risk for HFD
personnel and citizens as well. Through analyzing correlations, visualizing data, and creating helpful software tools, we have worked to provide suggestions for the HFD’s motor vehicle incident report and review procedures to aid them in preventing HFD motor vehicle collisions in the future.
- Team Members: "Houston Fire Department (HFD)"
- Junwei Chen (Master of Electrical and Computer Engineering, Fall 2021)
- Sheng Cheng (Master of Computer Science, Fall 2021)
- Yuanhao Dong (Master of Data Science, Fall 2021)
- Durga Parulekar (Master of Computer Science)
- Colleen Skinner (Statistics, 2023)
- Xingya Wang (Mathematics, Fall 2024)
- Sponsor Mentor: Leonard N. Chan (Accreditation Manager), Michael A. Marino (District Chief)
- D2K Fellow Mentor: Ahmed Imtiaz Humayun (PhD student)
- Rice Faculty Mentor: Prof. Arko Barman
Project Title: Texas Children’s Heart Center Registry Abstraction 
- Project Description: We employ Natural Language Processing techniques to automate the extraction of key patient information from clinical notes at Texas Children’s Hospital. The impact of our project is to facilitate the transfer of
TCH patient information to an international registry, thus saving TCH nurses’ time.
- Team Members: "Save the ChildreNLP"
- Mahmoud Al-Madi (Class of 2023 - BS in Electrical and Computer Engineering)
- Timofey Efimov (Class of 2023 - BS in Electrical and Computer Engineering)
- Alex Holzbach (Class of 2024 - BS in Electrical and Computer Engineering, BA in Mathematics)
- Robert Kenworthy (Class of 2023 - BS in Electrical and Computer Engineering)
- Michael Tang (Class of 2023 - BS in Electrical and Computer Engineering, BA in Mathematics)
- Alexa Thomases (Class of 2023 - BS in Electrical and Computer Engineering)
- Sponsor Mentor: Di Miao (Senior Project Manager), Christian Jenson (Assistant Director Analytics & Insights)
- D2K Fellow Mentor: Dr. Jyotikrishna Dass (Research Scientist, D2K)
- Rice Faculty Mentor: Prof. Xinjie Lan
Project Title: Foster Child Advocacy Evaluation Using Survival Analysis, Causal Inference, and Autoencoders 
- Project Description: We evaluated the efficacy of Child Advocates’ program to help children
get placed into situations that will be beneficial to their growth and development.
- Team Members: "Child Advocates"
- Max Cunningham (Class of 2023 - B.A. Statistics, Sport Analytics)
- Jack Gray (Class of 2023 - B.A. Statistics, Sport Analytics)
- Andy Wang (Class of 2023 - B.A. Computer Science, Statistics)
- Zihe Zhao (Class of 2023 - B.S. Computer Science)
- Jiahui Yu (Class of 2023 - Professional Masters, Electrical and Computer Engineering)
- Chieh-Ju Chueh (Class of 2023 - Professional Masters, Data Science)
- Sponsor Mentor: Sonya Galva (Chief Executive Officer), Jane Zimbaldi (Grants Manager), Marshall West (Senior Manager of Technology and Strategy)
- D2K Fellow Mentor: Brian King (PhD student)
- Rice Faculty Mentor: Prof. Xinjie Lan
Project Title: Development of Machine Learning Algorithms for Precision Waterbird Monitoring 
- Project Description: Developed a Faster-RCNN based bird species detector that works on 20 different bird species.
To tackle the problem of fine-grained classification of visually similar species, we compared our results with a ResNet classifier baseline and used GradCAM to interpret our models.
- Team Members: "Audubon Computer Vision"
- Haixiao Wang (MS, Data Science, 2nd year)
- Linfeng Lou (MS, Data Science, 2nd year)
- Boning Li (PhD, Electrical and Computer Engineering, 5th year)
- Tony Gao (PhD, Statistics, 2nd year)
- Christopher Le (MS, Data Science, 2nd year)
- Sponsor Mentor: Hank M. Arnold (Audubon Texas Volunteer), Anna Vallery (Conservation Biologist), Richard Gibbons (Gulf Coast Program Manager at American Bird Conservancy)
- D2K Fellow Mentor: Krish Kabra (PhD student)
- Rice Faculty Mentor: Prof. Arko Barman
Project Title: Analysis of Annual Bird Counts 
- Project Description: The goal of this project is to accurately predict bird counts/trends to help in identifying species whose populations are increasing and decreasing and identify sources of variability in the annual Christmas Bird Count data.
- Team Members: "Audubon CBC"
- Andrew Whitig (Class of 2023 Statistics Professional Masters)
- Michael Kelley (Class of 2023 B.S. Statistics)
- Lynn Niu (Class of 2023 B.S. Statistics/Computer Science)
- Xilin Song (Class of 2023 Data Science Professional Masters)
- Tianjun Chen(Class of 2023 Master of Computer and Electrical Engineering)
- Sponsor Mentor: Hank M. Arnold (Audubon Texas Volunteer)
- D2K Fellow Mentor: Huiyuan Yang (Postdoc)
- Rice Faculty Mentor: Prof. Arko Barman
Project Title: Predicting a patient’s risk of Alzheimer’s based on physical, mental, blood biomarker and protein biomarker attributes 
- Project Description: 5.8 million people in the U.S. are living with Alzheimers’ disease, a number which is estimated
to triple over the next four decades. This disease not only makes a person experience memory loss, it also strips them of independence and causes a change in mood, personality and behavior. Current diagnoses for such a neurodegenerative disorder involves tedious testing and scrutiny. Our aim is to utilize our data science and machine learning skills to examine physical, mental, blood and protein biomarker attributes of patients and use those attributes to predict the likelihood of
early-onset Alzheimers’ with a degree of accuracy similar to that of traditional methods.
- Team Members: "Forget-me-not"
- Angela Cao, Master of Data Science, 2022
- Anusha Muddapati, Master of Computer Science, 2022
- Sophia Prieto, Bachelor of Statistics, 2023
- Wei Ren Gan, Master of Data Science, 2023
- Tejeshwine Viswanathan, Master of Electrical and Computer Engineering, 2022
- Sponsor Mentor: Dr. John Broussard (UTHealth/TARCC)
- D2K Fellow Mentor: Alicia Choto Segovia (PhD student)
- Rice Faculty Mentor: Prof. Arko Barman
Project Title: Predicting Question Quality and Suggesting Intelligent Improvements for Stack Overflow Posts 
- Project Description: Stack Overflow is becoming overly saturated with vague, uninformative content that halts both developer productivity, and the flow of knowledge. Our project applies state-of-the-art Natural Language Processing techniques and models to predict question quality and suggest improvements for users.
- Team Members: "Stack Overfit"
- Alex Elkin (Class of 2023 - Computer Science, Data Science)
- Anthony Yan (Class of 2024 - B.S. Computer Science)
- Bhavesh Shah (B.S. Computer Science, Minor in Data Science - Expected Dec. 2022)
- Wu Angela Li (MECE Electrical and Computer Engineering, Expected Dec. 2022)
- D2K Fellow Mentor: Yuxin Tang (PhD student)
- Rice Faculty Mentor: Prof. Xinjie Lan