This project encompasses a Python application that predicts airline passenger demand using regression models and artificial neural network methods. The project includes steps for data analysis, model training, and performance evaluation.
Python: The project is written in the Python programming language. NumPy: Utilized for numerical computations and data manipulation. Pandas: Employed for data analysis and processing. Matplotlib and Seaborn: Used for data visualization. scikit-learn (sklearn): Utilized as a library providing machine learning algorithms and tools. MLPRegressor (Artificial Neural Network Regression Model): Used to create artificial neural network-based regression models. The project can be initiated by running the main component file, HavayoluYolcuTahmini.py. This file loads the dataset, trains the model, makes predictions, and evaluates the results. Data Loading: The dataset is read from the HavayoluYolcu.csv file. Data Preprocessing: Dependent and independent variables are separated. The dataset is split into training and testing sets. Data normalization is performed. Model Training: Various regression models and an artificial neural network model are trained. Performance Evaluation: The prediction performance of each model is evaluated, and metrics are calculated. Results Visualization: The relationship between predictions and actual values is visualized through graphs. The performance of the models is evaluated using the following metrics:Mean Absolute Error (MAE) Mean Squared Error (MSE) Root Mean Squared Error (RMSE) R2 Score
The project evaluates the proximity of predictions to actual data and the performance of the models. Additionally, graphs depicting the predictions of regression models are created.