The Data Science and Analytics Unit at the ASU Library is excited to announce the return of our Volunteer Open Projects. We have four (4) Spring 2024 Open Projects to choose from this semester. The Volunteer Open Projects are an opportunity to get involved in real-world issues in which to collaborate, learn, and expand your knowledge and expertise in data science and analytics, regardless of your discipline or level of experience.

This 90-minute in-person kickoff session is for current ASU students of all levels and disciplines who desire to collaborate and expand their knowledge in data science and analytics no matter one’s discipline and level. The Volunteer Open Project kickoff will be conducted in-person, seats limited for in-person attendees as a pizza lunch will be served.

Important details:

• Friday, January 19, 2024, 12 – 1:30 pm
• Registration required - unsure if you can attend in-person, please register for the Remote (Zoom) option.
• Please register using your ASU email.
• Time is based on Arizona time.

Brief details for each project: 

• Transformative potential of Machine Learning in healthcare - Breast Cancer and Chronic Kidney Disease (CKD) This project aims to explore the transformative potential of machine learning techniques within the healthcare sector to offer the potential to enhance the precision and speed of breast cancer diagnosis and detect CKD to empower healthcare providers to identify at-risk individuals, implement preventive measures, and tailor treatment plans.

• Pneumonia detection This project endeavors to investigate the potential capabilities of machine learning in the health sector, concentrating on the detection and prognosis of Pneumonia. Pneumonia remains a leading cause of morbidity and mortality worldwide, necessitating accurate and rapid diagnosis. Machine learning models can aid in the early detection and differentiation of pneumonia cases, assisting healthcare professionals in making informed decisions about patient care.

• Credit card fraud detection This project aims to tackle the challenge of distinguishing between legitimate and fraudulent credit card transactions using machine learning techniques such as anomaly detection, logistic regression, Support Vector Machines (SVM), and Random Forests and then critically evaluate which technique(s) provides better prediction.

• Violent vs Non-violent Conflict This project focuess on two distinct types of conflict. Armed conflict, encompassing interstate and civil wars, as well as recurrences of such conflicts. Nonarmed conflict, which includes protests, sit-ins, strikes, and similar nonviolent resistance methods. This project will apply various Machine Learning to discern the impact of recognized conflict drivers on model accuracy, particularly in validation and testing phases.