AbstractBackgroundMobile app‐based, high‐frequency monitoring of cognition holds the promise to facilitate the individual detection of cognitive change. However, there are several factors in everyday life that potentially influence estimates of cognitive performance in an unsupervised remote test setting. Characterizing these factors is critical to guide the interpretation of results from mobile app‐based studies of cognitive function in the future.MethodsWe conducted a Germany wide Citizen Science Project (after accreditation with the Citizen Science Portal of the German Ministry for Science and Education) with the goal to identify everyday life factors influencing cognitive performance estimates acquired via smartphone‐based assessments. To that end, every participant was pseudo‐randomly assigned to one of three memory tests: 1) pattern separation of objects and scenes (Berron et al., 2018, 2019); 2) complex (photographic) scene recognition memory (Düzel et al., 2011, 2018); 3) pattern completion of object‐in‐scene associations. Participants were asked to perform one test per week over a period of 15 weeks.Results1765 participants (70% female) completed 7900 weekly test sessions. The age‐range of participants was between 18 and 89 years of age. Mean age was 53 (SD=15). We found significant effects of age, time of the day of test performance, time between encoding and retrieval as well as the screen size of the mobile device. Further, our results indicate minor or even no practice effects with repeated tests and indicate that between 4‐5 test sessions are sufficient in order to define a measure of baseline performance.ConclusionOur results indicate several factors influencing cognitive measures in an unsupervised setting of remote smartphone‐based assessment of memory functions. While some factors were specific to only some tests, most factors were associated to all three tests suggesting that they are of general nature. Finally, several sets of different parallel test versions for each memory test resulted in marginal practice effects with repeated assessments.