| dc.description.abstract | This review explores the application of data analytics to enhance personalization in
fitness tracking systems, a growing need within the expanding domain of wearable
and mobile health technology. Although fitness trackers have made significant strides
in capturing data on daily activity and health metrics, most remain limited to basic
descriptive insights, which restrict their potential for adaptive user engagement. By
categorizing existing research through the PRISMA approach, this paper investigates
how advanced analytics—descriptive, predictive, and prescriptive can contribute to
personalized fitness guidance. While descriptive analytics offers foundational insights
into daily metrics, predictive analytics enables anticipatory adjustments in fitness
regimens, and prescriptive analytics provides actionable recommendations. The study
identifies several promising opportunities and highlights challenges, such as privacy,
algorithmic biases, and the need for robust real-time data processing. The findings of
the study suggest that integrating predictive and prescriptive models could advance the
field by delivering a deeper, more tailored user experience in fitness tracking, ultimately
supporting sustained fitness improvement and adherence. | en_US |
