App search ranking prediction towards enhanced app store optimization using ML and NLP

Application Store Optimization is an emerging field which aims at enhancing applications’ standing in search results of application stores. The ASO-controlled features that include app title, descriptions and screenshots are focused and optimized to gain a high ranking as part of the ASO Strategy. This study filled the research gap by analysing the influence of app factors on the keyword rankings of the app through machine learning-based predictions. This novel study proposed a supervised machine learning classification model to predict the app title keyword ranking through a diverse set of features, such as user-related, developer-controlled- and platform-controlled groups. It helps to understand their collective impact on the search rankings of apps in the Google Play Store. Various classification models are compared based on performance measures such as accuracy, precision, recall and F1-score, and the highest accuracy of 75 percent in classifying apps from ranking classes of “High”, “Medium”, and “Low” was achieved with the SVM model. The study revealed that ASO-Controlled features are among the most influential features affecting the model's performance. Thus, it highlights the importance of ASO-controlled factors in an effective app growth strategy to achieve a high ranking and application success. Moreover, the study not only provided ASO practitioners with directions towards enhanced ASO strategies but also paved the way for them to contribute to the ever-dynamic field of App Store Optimization.