Directions
Use the Companies tab to view all projects by company
Use the Search tab to search for projects by domain, keywords, and meeting time
Click on individual projects to view more information including project descriptions from corporate partners
BASF - Market Indicators for Trend Identification
Open for Registration- Lecture time: Thursday: 13:30:00 - 14:20:00 ET
- Lab time: Tuesday: 13:30:00 - 15:20:00 ET
- Domain: Agriculture
- Keywords: Agriculture, Market Development
- Tools: Data Exploration, Feature Engineering, Machine Learning, Python, Time Series Data Analysis
- Citizenship: Open to all students
Summary
In the ever-evolving world of agri-business, understanding market trends and predicting future prices is crucial for strategic decision-making. The project aims to combine various market indicators to identify trends and forecast prices in key market areas.
AgReliant Genetics - Customer Segmentation & Prediction
Open for Registration- Lecture time: Tuesday: 13:30:00 - 14:20:00 ET
- Lab time: Thursday: 13:30:00 - 15:20:00 ET
- Domain: Agriculture
- Keywords: Agriculture, Classification, Customer Behavior, Data Exploration, Data Exploration, Machine Learning, Prediction
- Tools: Classification, Excel, Machine Learning, marketing analytics, Python, R, Snowflake, Tableau
- Citizenship: Open to all students
Summary
AgReliant wants to greatly increase the efficiency with which AgReliant sells to customers. We want to use Data Science and Machine Learning techniques to gain a better understanding of our customer base through segmentation and predictive behavior modeling.
- Lecture time: Tuesday: 15:30:00 - 16:20:00 ET
- Lab time: Thursday: 15:30:00 - 17:20:00 ET
- Domain: Real Estate
- Keywords: Data Scraping, Machine Learning, Real Estate Property
- Tools: Databases, Data Modeling, GitHub, Machine Learning, MongoDB, Optimization, Predictive Models, Python
- Citizenship: Open to all students
Summary
Create a data model within the parameters of our current website/tech stack that identifies employment, life development, and housing opportunities based on end-user statistics.
NIIMBL - Simulated Manufacturing
Open for Registration- Lecture time: Monday: 09:30:00 - 10:20:00 ET
- Lab time: Friday: 09:30:00 - 11:20:00 ET
- Domain: Pharmaceutical
- Keywords: Data Analytics, Experimental Data Modeling, Manufacturing
- Tools: Data Modeling, Ontology Development, Python, R
- Citizenship: Open to all students
Summary
Create rich manufacturing datasets by combining models based on data from small, designed experiments with simulated inputs which have random variance built in.
Viasat - Art of Space Warfare: Orbital Modeling of Cascading Effects from Debris based on Space Consumption
Open for Registration- Lecture time: Tuesday: 13:30:00 - 14:20:00 ET
- Lab time: Thursday: 13:30:00 - 15:20:00 ET
- Domain: Research and Development
- Keywords: Orbital Modeling, Satellite, Space
- Tools: Data Modeling, GitHub, Machine Learning, Python, R
- Citizenship: Open to all students
Summary
This project seeks to understand (via modeling) the thresholds of over population in space to assess a sustainable carrying capacity (considerate of risk/impact) that is driven by multiple threat scenarios.
Inogen - Field-Repairable Oxygen Concentrator
Open for Registration- Lecture time: Monday: 15:30:00 - 16:20:00 ET
- Lab time: Wednesday: 15:30:00 - 17:20:00 ET
- Domain: Biomedical Engineering
- Keywords: Biomedical Engineering, Documentation, Multi-Disciplinary, Oxygen Concentrator, Prototyping
- Tools: Electrical Engineering, Mechanical Engineering, Python, Software Engineering
- Citizenship: Open to all students
Summary
This Project will be in collaboration with mentors from Inogen and Purdue Biomedical Engineering students in EPICS. Mission: Build an oxygen concentrator (hardware & software) out of generic (non-proprietary) parts and prepare instructions how to repair the build if it breaks
- Lecture time: Friday: 15:30:00 - 16:20:00 ET
- Lab time: Monday: 15:30:00 - 17:20:00 ET
- Domain: Aerospace
- Keywords: Aerospace, Machine Learning, Prediction, Predictive Modeling, Trajectory Analytics
- Tools: Git, Jupyter Notebooks, Machine Learning, Python, Tracktable (Sandia Python library)
- Citizenship: U.S. Citizens Required
Summary
This project will focus on trajectory prediction and analysis. Observing trajectories that have crossed an area or recovering lost segments. Predicting where the trajectory will be after a certain amount of time and where the vehicle will be.
- Lecture time: Thursday: 12:30:00 - 13:20:00 ET
- Lab time: Tuesday: 11:30:00 - 13:20:00 ET
- Domain: Manufacturing
- Keywords: Aerospace, Analytics, Business Intelligence, Data Cleaning, data mining, Data Visualization, Machine Learning, Predictive Analysis, Sales Forecasting
- Tools: Data Analytics, Machine Learning, Power BI, Python, R, Tableau
- Citizenship: Open to all students
Summary
Develop a predictive model by leveraging advanced analytics and machine learning techniques, the project aims to provide an accurate sales forecast that in turn enhances internal inventory management, optimizes supply chain operations, and improves sales strategies.
- Lecture time: Friday: 09:30:00 - 10:20:00 ET
- Lab time: Monday: 09:30:00 - 11:20:00 ET
- Domain: Pharmaceutical
- Keywords: Agile, Lean Framework, Pharmaceutical, PowerBI, Tulip
- Tools: App Creation & Design, Data Analytics, Power BI, Tulip
- Citizenship: Open to all students
Summary
AstraZeneca currently has business need to advance digital tools within Tulip and PowerBi. Students will be expected to build Tulip/PowerBi apps from creation to implementation and enhance the current standard work instructions for creating apps.
Frederick National Laboratory (FNL) - Analysis of Spatial Single-Cell Datasets
Open for Registration NDMN/IDM- Lecture time: Tuesday: 15:30:00 - 16:20:00 ET
- Lab time: Thursday: 15:30:00 - 17:20:00 ET
- Domain: Biomedical Research
- Keywords: biology, Biomedical Science, Clustering, SPAC, Spatial Analysis, Transformation, Visualizations
- Tools: GitHub, Python, R
- Citizenship: Open to all students
Summary
To accelerate the pace of delivering tools to analyze spatial single-cell datasets by leveraging the contributions of students and to contribute to the advancement of scientific knowledge and understanding in the field of single-cell biology and spatial analysis.