Summary of Admission Prediction in Undergraduate Applications: An Interpretable Deep Learning Approach, by Amisha Priyadarshini et al.
Admission Prediction in Undergraduate Applications: an Interpretable Deep Learning Approach
by Amisha Priyadarshini, Barbara Martinez-Neda, Sergio Gago-Masague
First submitted to arxiv on: 22 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed deep learning-based classifiers, Feed-Forward and Input Convex neural networks, address the challenges faced by traditional machine learning-based approaches in verifying undergraduate admissions. The existing methods lack scalability and suffer from performance issues when dealing with large volumes of data. To overcome these limitations, the authors incorporate an interpretability module, LIME, to provide insights into their model’s decision-making process. The training and test datasets consist of applicants’ data with a wide range of variables and information. Compared to the best-performing traditional approach, the proposed models achieve higher accuracy by a considerable margin of 3.03%. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make sure that universities can decide who gets in without bias. Right now, deciding who gets in is hard because there’s too much data to look at and it can be unfair. The old way of doing things doesn’t work well when there are many applicants. Some smart people came up with new ideas called Feed-Forward and Input Convex neural networks that make it easier and fairer. They also added a special tool to explain why they made certain decisions. This new way is better than the old way because it’s more accurate. |
Keywords
* Artificial intelligence * Deep learning * Machine learning
