Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/dronabopche/100-ML-AI-Project/llms.txt

Use this file to discover all available pages before exploring further.

Supervised learning projects in this repository span two core problem types: regression, where the goal is to predict a continuous numeric value, and classification, where models assign inputs to discrete categories. Each project in this section uses real-world tabular datasets sourced primarily from Kaggle, and follows a consistent architecture that includes a preprocessing pipeline, trained model artifacts, and a Flask-based prediction API.

House Price Prediction

Predict residential sale prices using an ensemble of Linear, Ridge, and Lasso regression models with a Gemini-powered preprocessing layer.

Employee Retention Prediction

Classify employee turnover risk using three logistic regression variants with confidence scoring across all model outputs.

Medical Cost Prediction

Estimate individual insurance charges from demographic and health features using linear models and CatBoost.

Titanic Survival Prediction

Apply binary classification to the classic Titanic dataset to predict passenger survival based on socioeconomic and demographic factors.

Email Spam Classification

Detect spam emails using NLP-based feature extraction and classification models trained on labeled message corpora.

Credit Loan Approval

Predict binary loan approval outcomes from applicant financial and credit profile features using ensemble classifiers.

All supervised learning projects

The table below lists all supervised learning projects in the repository (range 01–27), their problem type, and dataset source.
#ProjectProblem typeDataset source
01House Price PredictionRegressionKaggle
02Employee Retention PredictionClassificationKaggle
03Iris Flower ClassificationClassificationKaggle / UCI
04Medical Cost PredictionRegressionKaggle
05Titanic Survival PredictionClassificationKaggle
06Email Spam ClassificationClassificationPublic ML repositories
07Energy Power PredictionRegressionKaggle
08Smart Shop PredictionRegressionKaggle
10Used Car Price PredictionRegressionKaggle
11Mobile Price Range PredictionClassificationKaggle
13Hotel Booking Cancellation PredictionClassificationKaggle
14Crop Yield PredictionRegressionKaggle
18Password Strength PredictionClassificationKaggle
19Health Risk PredictionClassificationKaggle
20Personality PredictionClassificationKaggle
23YouTube Video Popularity PredictionRegressionKaggle
26Credit Loan ApprovalClassificationKaggle
27Amazon Product Price DeterminationRegressionKaggle

Standard project structure

Every supervised learning project follows the same directory layout, making it easy to navigate between projects and extend any pipeline.
Project_Name/

├── Dataset/          # Raw CSV files and tabular data
├── Models/           # Serialized model files (.pkl, .joblib)
├── Resources/        # Diagrams, visualizations, documentation assets
├── SRC/
│   ├── Processing/   # Preprocessing: encoding, scaling, feature engineering
│   ├── Output/       # Prediction logic, probability scoring, result formatting
│   └── App.py        # Flask API entry point

├── Project_Notebook.ipynb
├── requirements.txt
└── README.md
Projects that follow the full standard structure expose a POST /predict endpoint through App.py. Some earlier projects (05, 06, 26) are notebook-only and do not yet include a deployed API layer.

Build docs developers (and LLMs) love