The use of deep learning (DL) techniques for mobile learning is an emerging field aimed at developing methodsfor finding mobile learners’ learning behavior and exploring important learning features. The learning features (learningtime, learning location, repetition rate, content types, learning performance, learning time duration, and so on) act asfuel to DL algorithms based on which DL algorithms can classify mobile learners into different learning groups. In thisstudy, a powerful and efficient m-learning model is proposed based on DL techniques to model the learning process ofm-learners. The proposed m-learning model determines the impact of independent learning features on the dependentfeature i.e. learners’ performance. The m-learning model dynamically and intuitively explores the weights of optimumlearning features on learning performance for different learners in their learning environment. Then it split learnersinto different groups based on features differences, weights, and interrelationships. Because of the high accuracy of theDL technique, it was used to classify learners into five different groups whereas random forest (RF) ensemble methodwas used in determining each feature importance in making adaptive m-learning model. Our experimental study alsorevealed that the m-learning model was successful in helping m-learners in increasing their performance and taking theright decision during the learning flow.