Bonsai Applied Computations Group

Today we highlight Sebastian Gonzales-Portillo, project manager of Bonsai’s current Marketing Project. The team is currently working on performing sentiment analysis on a large database of political tweets and creating visualizations such as time series plots and other representations of data to draw meaningful insights. Previously Sebastian worked on our Neuroscience project team, helping create image processing algorithms to segment dendritic spine tif images to construct 3D images from a 2D image stack. When asked about membership within Bonsai, Sebastian said “Bonsai has been an incredible part of my professional and technical development. Getting to collaborate with talented, driven, and passionate people on real projects with real clients has helped me gain experience and insight into creating end-to-end products with tangible value.” Sebastian specializes in computer science, mathematics, and business technology. Currently, he is serving as a research assistant for Dr. Sarkar within the Computer Science department at the University of Miami. Sebastian also is the new member educator for the Kappa Theta Pi - Professional Technology Fraternity. Over the summer, he interned as a ML engineer at PadStats, a startup providing AI-powered data solutions for real estate professionals and investors.

In the Spring semester of 2024, Bonsai ACG’s marketing and business team led by Alexandr Kim, composed of Brendan Hendricks, Devon Mason, and Iris Grigoras undertook a significant Twitter data analysis project in partnership with the Marketing Department at the University of Miami Herbert Business School. The project, funded with a $5,000 budget, aimed to analyze and visualize geospatial trends across over 700,000 tweets. This large-scale data analysis effort provided deep insights into social media behavior and trends, offering invaluable information for both academic research and business applications. Our team began by managing the budgeting, data collection, and technical infrastructure needed to handle this vast dataset. We utilized Twitter’s professional API to gather the data, which included several millions of data points such as tweet content, tweet metadata, and user metadata. One of the main challenges we faced was that a significant portion of tweets lacked explicit location data, which was crucial for the geographic analysis we were tasked with conducting. To overcome this, we implemented geolocation inference using the Pigeo repository. This tool allowed us to infer the location of tweets even when explicit geotags were missing. However, one of the key challenges we encountered was understanding the dependencies of this older tool and learning how to effectively run subprocesses to make it function within our modern data pipeline. This required extensive research and trial-and-error as our team delved into documentation and community forums to troubleshoot compatibility issues and ensure smooth integration. By analyzing tweet metadata, including language and timezone information, we were able to estimate geographic data, enabling a robust analysis of social media trends by region. The data processing and analysis phase was extensive, involving the cleaning, sorting, and visualization of the tweet data using Python. Our team conducted an in-depth examination of the error rates associated with geolocation and data collection methods, ensuring the integrity of our findings. The final product was a series of visualizations and reports that illuminated social media trends across various geographic regions, offering both academic researchers and business analysts a powerful tool for understanding the dynamics of online communication. This project tested Bonsai Analysts’ ability to manage large-scale data collection and analysis efforts.

Today we spotlight Gabriel Huang, Project Manager of Bonsai’s Biology project. The team, in collaboration with multiple labs at the The Miami Project to Cure Paralysis, is tasked with constructing machine learning cell-to-cell communication models to analyze gene expression in damaged central nervous system tissue. Previously, Gabriel was an analyst in the computational neuroscience division, developing an AI tool to quantify dendritic spine morphology, a crucial step in analyzing neurodegenerative diseases such as Alzheimer’s and Parkinson’s disease. Reflecting on his time in Bonsai, Gabriel shared, “I love how Bonsai values the qualities I admire most in people: open-mindedness, curiosity, and creativity.” Gabriel has always been passionate about data science, but it was while he was working in the UM Sport Science department that he developed an interest in the intersection between data science and health research. Using computational methods to help UM athletes avoid deterioration and injuries, he realized the potential of applying innovative data science to real-world health problems. Currently, he is a data scientist for defense contractor Tiger Tech Solutions, helping to develop medical wearables used by clients including the US Department of Defense, Mount Sinai Medical Center, and UM Athletics. He builds data software to analyze biometric data and cognitive load of military personnel and high-level athletes. In parallel, he conducts research at the Sylvester Comprehensive Cancer Center, focusing on structural bioinformatics modeling using neural networks. Passionate about the AAPI community, Gabriel currently serves as the President of the Asian American Students Association at the University of Miami.

As work on our portfolio of research projects progresses, we want to highlight our achievements from the previous semester. Last Spring, Bonsai’s Quantitative Finance team, led by Samuel Pass, had an exciting opportunity to participate in IMC’s Prosperity-2, a highly competitive, 15-day long trading simulation. This event provided a unique platform for our team to apply quantitative analysis in a fast-paced, simulated marketplace, where real-time decision-making was key to maximizing returns. Throughout the competition, we focused on statistical arbitrage, a strategy that involves identifying pairs of assets whose prices move together but temporarily diverge. By using various forms of statistical analysis, our team was able to identify the ideal pairs for trading. We employed comprehensive backtesting techniques to evaluate the effectiveness of our strategies across historical data, assessing performance metrics such as realized profit and loss, Sharpe ratio, and drawdowns. In addition to statistical arbitrage, we implemented machine learning techniques to enhance our decision-making. A key innovation in this project was the development of a Jupyter notebook to identify optimal pair-candidates using k-means clustering, a method for grouping similar data points. To refine our entry and exit points, we utilized a Long Short-Term Memory (LSTM) model, a type of recurrent neural network that is particularly effective for forecasting time-series data. This allowed us to predict price movements and optimize our trading positions, giving us a competitive edge. For more information on the project, visit the projects tab at www.bonsaiacg.com and view the GitHub at https://lnkd.in/ePakWwe5?

A page to call our own:??????????????????????? Our website is now live. To view previous projects or apply to do research with us visit bonsaiacg.com. Thank you to analyst Andrew Rand Luthringer for the great work.

Bonsai’s team of the University's 32 select computer scientists has begun building out their research in 7 new fields. We look forward to sharing the details of our work in the coming weeks.

Founded in Spring 2024 by Alexandr Kim, Ethan Tieu, Samuel Pass, and Taylor Lin the Bonsai Applied Computations Group is an initiative focused on uniting the brightest minds in computer science with researchers seeking specialized expertise. Comprised of interdisciplinary talent, a majority of our members pursue dual majors alongside computer science, allowing them to draw from diverse fields of knowledge. Since the group's inception, members have applied their expertise to research in neuroscience, marketing, and quantitative finance. As we look ahead to the upcoming semester, the group has ambitious goals to expand and take on even more innovative projects.