The effect of feature selection with optimization on taxi fare prediction

Feature selection plays a key influence in machine learning (ML); the main objective of feature selection is to eliminate irrelevant and redundant variables in different classification problems to improve the performance of the learning algorithms. Classification accuracy is improved by reducing the number of selected features. Many real-world problems, such as taxi fare can be predicted by ML. This paper proposes feature selection using genetic algorithm (GA) optimization to predict taxi fare. Experiments are performed on real datasets of taxi fare, and this paper uses eight classifiers to evaluate the selected features. The performance of the classifiers is assessed using various performance metrics. The results are compared with feature selection without optimization. The proposed method records high classification accuracy when evaluated by three types of classifiers (random forest, AdaBoost, and Gradient Boost). The results indicate that the prediction accuracy of the proposed method is 99.7% on taxi fare dataset.