Health Insurance Cross-Sell Prediction

[siddhant4ds]

Closes: #74

• Title : Health Insurance Cross-Sell Prediction
• Name: Siddhant Tiwari
• Idenitfy yourself: SSOC-3 Contributor

Describe the add-ons or changes you've made 📃

Linked a notebook which includes:

1. Exploratory Data Analysis of the dataset
2. Data cleaning and preprocessing as required for different ML algorithms
3. Feature engineering
4. Feature selection based on statistical tests and feature-importances.
5. Models implemented: Logistic Regression, Linear Discriminant Analysis, Quadratic Discriminant Analysis, Gaussian Naive Bayes, K-Nearest Neighbors, Decision Tree, Random Forest, AdaBoost, Multi-Layer Perceptron neural network, XGBoost, CatBoost and LightGBM
6. Post-tuning of prediction thresholds for models for more accurate predictions.
7. Result analysis using classification report along with ROC-AUC and Matthew's correlation coefficient.

Added a README which includes the project details and images generated.

Type of change ☑️

What sort of change have you made:

• New feature (non-breaking change which adds functionality)

How Has This Been Tested? ⚙️

Reproducibility: Fixed random seed for all experiments and multiple runs to check consistency.
Dependencies: Reran notebook on local environment as well as cloud-hosted notebook (Kaggle).

Checklist: ☑️

• My code follows the Contributing Guidelines & Code of Conduct of this project.
• This PR does not contain plagiarized content.
• I have performed a self-review of my own code.
• I have commented my code, particularly wherever it was hard to understand.
• My changes generate no new warnings.

Screenshots 📷

Note to reviewers 📄

[github-actions]

Thank you for submitting your pull request! We'll review it as soon as possible. For further communication, join our discord server https://discord.gg/tSqtvHUJzE.

[siddhant4ds]

@Avdhesh-Varshney Requesting a review. Thanks.