Flight delay predictions are crucial in helping passengers make informed decisions, optimise business strategies, and enhance service offerings. Accurate predictions enable airports to improve operational efficiency, reduce financial losses, and increase customer satisfaction. On the contrary, unreliable prediction systems can decrease passenger satisfaction, disrupt the travel journey, and negatively impact airport revenue. In response to these challenges, this study presents a pipeline that combines a Convolutional Neural Network (CNN) with a Random Forest (RF) model for predicting flight delays using a secondary dataset. The CNN extracts essential features from the flight delay data, which are then processed by the RF classifier and regressor to make precise predictions. The models were rigorously evaluated using different metrics such as accuracy, precision, recall, F1-Score, Mean Absolute Error, and Root Mean Squared Error. The results indicate that the CNN-RF classification model achieved over 90% accuracy, along with high precision, recall, and F1 scores. In addition, the CNN-RF regression model exhibited excellent predictive performance, with minimal errors and a high level of variance explained. Different scenarios are investigated to understand the real-time usage of the models developed. These findings suggest that the developed models offer reliable flight delay predictions and provide valuable insights for airport managers, benefiting both businesses and travellers.