In recent years, extensive research and development efforts have been increasingly carried out in both academia and industry to optimize the safety, efficiency, and environmental impact of vehicles traveling on roads. This study aims to contribute to these efforts by focusing on determining the driver’s driving style. The approach of our study is crucial for enhancing driving safety and optimizing fuel efficiency. Data science and machine learning techniques were employed to identify the driver’s driving style based on data collected during specific driving activities. Comprehensive driving data from various vehicle types were gathered as speed-time series using a global positioning system-based mobile application. The extracted features underwent necessary preprocessing and transformation to ensure their suitability for machine learning models. The prepared dataset was applied to k-nearest neighbors, support vector machine, decision tree, artificial neural network, logistic regression, naive Bayes, random forest, and light gradient boosting machine models. Three distinct driving styles were predicted: aggressive, normal, and calm. The accuracy rates achieved were 98.6% on residential district roads, 95.5% on urban roads, and 100% on motorways, with decision tree-based algorithms proving to be the most effective.