Forecasting methods application in the mobile app market in Turkey

Mobile applications have become a growing market in recent years all over the world and in Turkey. With the increase in the use of technology in our lives, it is expected to grow even more in the future. Understanding the dynamics of this growing market is important for both users and application owners. When the variables of mobile applications in different categories are examined, it is seen that they have different patterns. In this environment where the behavior of the users varies, the question of which parameters should be modeled and how they should be interpreted comes to mind. Within the scope of this study, monthly downloads and monthly active users time series data of 5 different mobile applications from the categories of e-commerce, e-scooter and social media between 2016-2022 were investigated using Autoregressive Models. As a result of the models, GARCH(1,1) for e-commerce and e-scooter applications; ARMA(1,1) model was found to be the most suitable for social media applications. The patterns shown by different mobile applications were estimated using the most appropriate models. As a result, in order to understand the dynamics of the mobile application market, both new entrants and applications operating in the existing market were shed light on. Insights on different categories were presented with numerical analyzes on time series and interpreted with an interdisciplinary perspective. The market was approached both holistically and in detail.