The purpose of this project is create a predictive model capable of identifying the probability of a person securing an admit based on their personal profile parameters. This dataset was built with the purpose of helping students in shortlisting universities with their profiles. The predicted output gives them a fair idea about their chances for a particular university.
- Inferential Statistics
- Machine Learning
- Feature Engineering
- Predictive Modeling
- Deep Learning
- Data Visualization
- Python
- Pandas, TensorFlow, SkLearn
- Collab
- This Notebook is based off an open source dataset available on www.kaggle.com where I have created models to predict the chances of a student securing a graduate admission based on thier profile! various parameters have been taken into accomodation. Performed scaling and dimentionality reduction based on VIF for getting better results. The Best Mean Squared Error (MSE) Numeric Obtained By a Few Models was: 0.0641 and an Accuray of About 80%
- All models are subject to betterment with more stringent hyper-parameter tuning. This can be achieved by random selection, brute force methods, etc. Various other classifiers can also be used, but the most standard classifiers have been considered in this notebook.
- Recommend standard practices for data transformation, outlier detection, and null value substitution have been incorporated in this notebook.
- Visualizations include scatter plots and hist plots!
This dataset is inspired by the UCLA Graduate Dataset. The test scores and GPA are in the older format. The dataset is owned by Mohan S Acharya.
This dataset was built with the purpose of helping students in shortlisting universities with their profiles. The predicted output gives them a fair idea about their chances for a particular university.
Mohan S Acharya, Asfia Armaan, Aneeta S Antony : A Comparison of Regression Models for Prediction of Graduate Admissions, IEEE International Conference on Computational Intelligence in Data Science 2019
- Feel free to contact team leads with any questions or if you are interested in contributing!
- https://www.linkedin.com/in/akarshsinghh/