About
MY BACKGROUND
I am a Purdue University graduate with dual B.S. degrees in Data Science and Applied Statistics with three years of interdisciplinary research experience including work with Purdue’s Rosen Center for Advanced Computing and Sustainable Transportation Systems Research Group. My research interests broadly lie in applied machine learning, optimization, and related quantitative methods.
Publications
WHAT I'VE WRITTEN
Generating Frequently Asked Questions from Technical Support Tickets using Large Language Models
Christina Joslin, David Burns, FNU Ashish, Elham Barezi, Ph.D.
12th International Workshop on HPC User Support Tools at Supercomputing (2025)
Used or New Electric Vehicles? Public Preferences and Market Segments
Bruno Cesar Krause Moras, Ph.D., Christina Joslin, Konstantina Gkritza, Ph.D.
International Journal of Sustainable Transportation (2025)
Presentations
WHERE I'VE PRESENTED
Summer 2025 Undergraduate Research Conference
(Virtual Presentation)
Purdue University, July 28 - August 1, 2025
Transforming Technical Support with Artificial Intelligence: Structured Question Generation from Support Tickets
Christina Joslin, David Burns, FNU Ashish
Spring 2025 Undergraduate Research Conference
(Poster Presentation)
Purdue University, April 8, 2025
Preference for Charging Station Venues - A Comparison between Electric Vehicle Users vs. Non-Electric Vehicle Users
Christina Joslin, Bruno Cesar Krause Moras, Ph.D., Konstantina Gkritza, Ph.D.
2025 Transportation Research Board Annual Meeting
(Poster Presentation: TRBAM-25-02448)
Washington DC, January 6, 2025
Used or New? Investigating Consumer Preferences in the Electric Vehicle Market
Bruno Cesar Krause Moras, Ph.D., Christina Joslin, Konstantina Gkritza, Ph.D.
NEXT-GEN Transport Systems Conference
(Poster Presentation)
Purdue University, September 21-22, 2024
Best Poster Presentation Award
Does Experience Shape Perceptions? A Comparison of Users' and Non-Users' Views on Electric Vehicle Characteristics
Christina Joslin, Bruno Cesar Krause Moras, Ph.D., Konstantina Gkritza, Ph.D.
Projects
WHAT I’VE CREATED
PromptBeaver
Description: Developed PromptBeaver, a prompt engineering tool designed to help undergraduate students studying CS/DS/AI build, analyze, and refine prompts for LLMs. Rather than generating answers directly, PromptBeaver guides users toward crafting stronger prompts that elicit customized conceptual explanations to simulate the type of iterative learning support students might receive during TA or professor office hours. Hosted as a Streamlit web application, the platform features two core workflows: Build a Prompt and Analyze My Prompt. This project was developed as part of Purdue University’s CS 475 Human-Computer Interaction course in Spring 2026.
ML Job Compass
Description: Created ML Job Compass, a Streamlit dashboard that guides students and professionals in charting career paths in machine learning. Using natural language processing, Retrieval-Augmented Generation (RAG), and data visualization, the app analyzes over 1,000 U.S. job postings to highlight domain-specific skill demands. Users can explore industry trends, then generate personalized skill checklists or phased roadmaps tailored to their target role and specialization. The system leverages a local Chroma vector store with an Ollama-backed LLM (i.e., Granite-3.3) for grounded recommendations, and supports deployment via Docker Compose or local Python environments. A manuscript based on this work has been submitted for publication.
Dog and Cat Breed Classifier with MobileNetV2 Transfer Learning
Description: This project implements a Convolutional Neural Network (CNN) in Python to classify images from 104 dog and cat breeds, utilizing a dataset of 29,000 images. The MobileNetV2 architecture, known for its efficiency and scalability, was used with transfer learning to achieve an F1 score of 84% on the test set. Key components include data preprocessing, model training with early stopping, and comprehensive evaluation metrics, making the model suitable for large-scale image classification tasks.