Personality Classification

Project Overview

This project aims to classify personality types based on responses to a psychological test. Using a dataset of responses to a 60-question test (with scores ranging from -3 to 3), the goal is to develop a machine learning model that can accurately predict one of the 16 distinct personality types (MBTI types). This is a challenging multi-class classification task with applications in psychology, human resources, and self-assessment tools.

---

Technical Highlights

• Dataset: Kaggle - 60k responses of 16 Personalities Test (MBTI)
• Size: 59,999 entries, 62 columns.
• Key Features:
  • 60 numerical features representing responses to a personality test.
• Approach:
  • Data Cleaning: The dataset was clean with no missing values or duplicates. The Response Id column was dropped as it is a unique identifier.
  • Exploratory Data Analysis: The code checks basic statistics, null values, duplicates, and unique values for all columns. The target variable Personality is well-balanced across all 16 classes.
  • Label Encoding: Applied to the target Personality column to convert it into a numerical format for multi-class classification.
  • Multi-class Classification: The target variable Personality has 16 distinct categories.
  • Models Used:
    • Logistic Regression, Ridge Classifier, SVC, Random Forest, XGBoost, AdaBoost, Gradient Boosting, Bagging, Decision Tree.
• Best Accuracy:
  • 97.7% with XGBoost Classifier.
  • 97.4% with Random Forest Classifier.
  • 94.5% with Gradient Boosting Classifier.
  • The very high accuracies for the ensemble models suggest that the test responses provide very strong discriminative power for personality classification.

---

Purpose and Applications

• Automated Personality Assessment: Enables a quick and accurate classification of personality types from test responses.
• Psychological Research: Supports research in personality psychology and behavior analysis.
• Human Resources: Assists in team building, career guidance, and job-role matching.
• Self-Improvement: Provides a tool for individuals to better understand their own personality traits.

---

Installation

Clone the repository and extract the data from the zip file.

Install the necessary libraries:

pip install pandas numpy seaborn matplotlib scikit-learn xgboost

---

Collaboration

We welcome contributions to improve the project. You can help by:

• Performing comprehensive hyperparameter tuning and cross-validation for the top-performing models to ensure robustness.
• Investigating the impact of different preprocessing techniques.
• Adding explainability (e.g., SHAP or LIME) to understand which questions or groups of questions are the most critical for classifying a specific personality type.