The competition aims to tackle the challenge of predicting student dropout from Online Courses.
- This Kaggle competition is organized by the Data Science Hub, Northeastern University.
- The competition aims to tackle the challenge of predicting student dropout from Online Courses.
- As the demand for online education skyrockets, understanding student behavior becomes paramount. With dropout rates posing a significant challenge, the need for accurate predictions is more pressing than ever. Imagine being able to identify at-risk students before they disengage, providing timely interventions and support to keep them on track.
- Python
- Machine Learning
- Scikit-Learn
- Metastatic TNBC is considered the most aggressive TNBC and requires urgent and timely treatment. Unnecessary delays in diagnosis and subsequent treatment can have devastating effects in these difficult cancers. Differences in the wait time to get treatment is a good proxy for disparities in healthcare access.
- The primary goal of building these models is to detect relationships between demographics of the patient with the likelihood of getting timely treatment. The secondary goal is to see if climate patterns impact proper diagnosis and treatment.
- Gilead Sciences is the sponsor for this year’s WiDS Datathon. They provided a rich, real-world dataset which contains information about demographics, diagnosis and treatment options, and insurance provided about patients who were diagnosed with breast cancer. The dataset originated from Health Verity, one of the largest healthcare data ecosystems in the US. It was enriched with third party geo-demographic data to provide views into the socio economic aspects that may contribute to health equity. For this challenge, the dataset was then further enriched with zip code level climate data.
- Data Science
- Machine learning
- Feature selection
- Regression
- Scikit-learn
- Tableau
- Python
Predict the duration of time it takes for patients to receive metastatic cancer diagnosis.
