This project involves exploring and analyzing a recruitment dataset, conducting machine learning experiments, ensuring fairness, and optimizing models. Below is an overview of the project:
The main objective of this project is to analyze a recruitment dataset, identify patterns, and describe its characteristics. Furthermore, machine learning experiments are conducted to develop predictive models for recruitment decision-making. The focus is on optimizing the performance of the best two models while considering and ensuring fairness in the process.
The dataset contains information about candidates applying for positions, including attributes such as gender, age, nationality, sports background, university grade, involvement in extracurricular activities, language proficiency, study background, and degree.
The source of the dataset is: https://www.kaggle.com/datasets/ictinstitute/utrecht-fairness-recruitment-dataset/data
-
Exploratory Data Analysis (EDA):
- This file contains exploratory analysis to understand the structure and characteristics of the dataset.
-
Machine Learning Experiments:
- This file includes experiments with various machine learning algorithms to develop predictive models for recruitment decision-making. Additionally, it includes a section on fairness check appended after the experiments.
-
Model 1:
- This file presents the development and optimization of the Support Vector Machine based on the recruitment dataset.
-
Model 2:
- This file presents the development and optimization of the Random Forest model based on the recruitment dataset.
- The EDA provides insights into the dataset's structure and characteristics, aiding in feature selection and understanding.
- Machine learning experiments help in developing predictive models for recruitment decisions.
- Fairness checks ensure that the models are not biased towards certain demographic groups.
- Models 1 and 2 represent the best-performing models, optimized for recruitment decision-making.
This project aims to apply data analysis and machine learning techniques to improve the recruitment process by identifying suitable candidates effectively and ensuring fairness in the decision-making process.
For further details, refer to the individual files within the project repository.