PREDICTIVE MODELLING OF MENSTRUAL CYCLE LENGTH USING MACHINE LEARNING AND TIME-SERIES ANALYSIS

The fundamental goal of this research is to create a machine learning predictive model that can forecast the length and timing of menstrual cycles. Using technical breakthroughs, this initiative addresses the intricacies of menstrual cycles, such as hormonal swings and individual variances, in order to improve ovulation and menstrual forecast accuracy. The application of computational intelligence techniques such as deep learning and machine learning shows promise in reproductive health, prediction, decision support systems, and illness diagnostics. Menstrual cycles vary substantially throughout a woman's life, generally getting longer or lighter with age and culminating in menopause, which commonly occurs in the late 50s. This study examines the efficacy of algorithms such as Linear Regression, Random Forest, ARIMA, and LSTM in properly forecasting menstrual cycles. The objective is to provide a valuable contribution to personal health management and wider medical applications. Key Words: machine learning, predictive model, menstrual cycles, hormonal fluctuations, ovulation, reproductive health, linear regression, random forest, LSTM, ARIMA