SMU Data Science Review
Abstract
Abstract: Forecasting the length and different phases of a woman’s menstrual cycle, especially ovulation, is an important aspect of family planning. Predicting fertility has many uses in family planning including avoiding pregnancy and assisting couples in becoming pregnant. Past methods have focused on monitoring basal body temperature (BBT), cervical mucus changes, and hormonal levels to determine fertility. While these methods can provide an accurate prediction of ovulation these tests can become expensive, time-consuming, and do not provide prediction until after ovulation has occurred. In this paper, we compare conventional fertility assessment that is based on a rule known as “three-over-six” to methods that employ machine learning methodologies to predict ovulation and forecast the most fertile time-frames during the ovulation cycle. We found that machine learning methodologies forecast a woman’s ovulation within one day of ovulation with 88% accuracy. Furthermore, through our study we can predict a woman’s ovulation before it happens based on her basal body temperature. We conclude that our methods can provide accurate prediction of ovulation and, thus, simplify family planning and reduce financial burdens associated with family planning.
Recommended Citation
Clark, Karen; Jain, Mridul; Messa, Araya; Le, Vinh; and Larson, Eric C.
(2018)
"Open Cycle: Forecasting Ovulation for Family Planning,"
SMU Data Science Review: Vol. 1:
No.
1, Article 2.
Available at:
https://scholar.smu.edu/datasciencereview/vol1/iss1/2
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Included in
Investigative Techniques Commons, Other Analytical, Diagnostic and Therapeutic Techniques and Equipment Commons
