Problem

Applying to graduate programs can be a daunting task, and students often struggle to determine their likelihood of acceptance. Admissions departments also face challenges in evaluating candidates based on a variety of factors. Our team was tasked with developing a solution that could accurately predict a student's chance of admission using key metrics.

I began by researching the most important factors that influence admissions decisions, including GRE and TOEFL scores, university rating, statement of purpose (SOP), letter of recommendation (LOR), CGPA, and research experience. I then needed to develop a model that could effectively analyze these variables and provide accurate predictions.

Solution

To create our predictive model, we employed Linear Regression analysis techniques. This allowed us to identify the most significant factors affecting admissions decisions and develop an algorithm that could accurately predict the likelihood of acceptance based on these variables.

I trained my model using a large dataset of past applicants' information and test scores. This enabled us to fine-tune the algorithm until it demonstrated strong performance metrics.

Impact

Increased accuracy in predicting admissions outcomes.

"This project has had an incredible impact on both applicants and admissions departments alike, providing greater transparency in the application process while streamlining evaluations."

Team

Rushikesh Choudhari - Data Scientist
- Developed the Linear Regression model and fine-tuned performance metrics
- Created the user interface for inputting data and receiving predictions

Learn more about our process here.

Predicting Grad School Admissions with Linear Regression