AirBnB Price Prediction Model based on large dataset.

Predictive Analysis in Python.

Objective: System explores a dataset of Airbnb property listings in London (per night) to develop a model for predicting prices. Using various machine learning techniques to enhance prediction accuracy.

Tools & Technologies Used

🧰 Libraries

• pandas, numpy – Data manipulation
• matplotlib, seaborn – Visualization
• scipy.stats – Statistical analysis
• sklearn – Preprocessing, modeling, and evaluation (Random Forest, cross-validation)
• tensorflow / keras – Deep learning model construction
• xgboost – Advanced gradient boosting regression model

🔍 Techniques

• Winsorization for outlier handling
• Feature scaling with StandardScaler
• Pearson correlation analysis
• t-tests for statistical differences
• Random Forest and XGBoost for regression
• Neural networks with TensorFlow/Keras
• K-Fold Cross Validation
• Model performance evaluation with:
  • Mean Absolute Error (MAE)
  • Root Mean Squared Error (RMSE)
  • R² Score