Model Selection and Hyperparameter Tuning for Improved Flight Delay Prediction

[FreeSpirit11]

Description

To enhance the performance of the flight delay prediction model, we should explore the use of more advanced machine learning models and perform hyperparameter tuning. The following steps should be taken:

1. Use Advanced Models:
   • Experiment with advanced models such as Random Forest, Gradient Boosting, and deep learning models like LSTM (if data is sequential).
2. Hyperparameter Tuning:
   • Use GridSearchCV or RandomizedSearchCV to find the best hyperparameters for the selected models.

Tasks

1. Implement Advanced Models:
   • Train and evaluate models like Random Forest, Gradient Boosting, and LSTM.
2. Hyperparameter Tuning:
   • Utilize GridSearchCV or RandomizedSearchCV to perform hyperparameter tuning for the selected models.
3. Evaluate Performance:
   • Compare the performance of these models with the current Decision Tree model using appropriate metrics like ROC AUC score.

Benefits

Using advanced models and optimizing hyperparameters is expected to improve the accuracy and robustness of the flight delay prediction model.

[FreeSpirit11]

Hi, @Niketkumardheeryan , I have raised this issue . Please assign it to me .

[invigorzz313]

There is a Flight_delay_prediction_project in the codebase. Do you mean to improve that?

[FreeSpirit11]

Yes I want to improve Flight_delay_prediction_project.

[FreeSpirit11]

Hi @invigorzz313 ,I have created the pull request. Please provide level 3 badge on this issue .