METHODOLOGY

How Plumm predicts your cycle so precisely.

Our algorithm doesn't guess. It learns from your real cycles, on clinical foundations. We explain it all, simply.

Day-accurate after 3 cycles

The more you log, the more the prediction sharpens. The algorithm learns from YOU.

8 clinical signals

Mucus, ovulation pain, libido, spotting… each weighted by the clinical literature.

Sources: Hilgers, Billings, ACOG

We cite our references — and ship them in our code.

METHODOLOGY · 01

The starting point: Ogino, only better

Most apps predict from an « average » 28-day cycle with ovulation on day 14. That's the Ogino method, a hundred years old — right for no one, because nobody has a perfectly average cycle.

Plumm starts there, then sharpens it with two things: your real cycle lengths, and the signals you log.

METHODOLOGY · 02

Your cycles, not an average

The moment you log your period, Plumm remembers your real cycles. With each new one, we recompute your average — giving more weight to recent cycles (your last 5 count more than those from 6 months ago).

Outlier cycles (under 15 or over 60 days) are filtered out. The result: your « average » cycle is yours. Not the population's.

METHODOLOGY · 03

8 clinical signals, each weighted

Other apps stop here. Plumm goes further: log physiological signals and we adjust your prediction in real time.

Each signal carries a weight drawn from clinical research: • Egg-white mucus (0.8) — the most reliable for spotting ovulation (Hilgers, Billings) • Watery mucus (0.6) — fertile window • Dry mucus after the peak (0.85) — ovulation has passed • Ovulation pain (0.8) • Libido peak (0.4) • Spotting (0.85) — cycle start • Premenstrual pain (0.5) • Premenstrual mood (0.4)

METHODOLOGY · 04

Yesterday counts more than last week

A signal has a shelf life. Yesterday's counts at 80 % of its weight, the day before at 64 %, and so on. Past 10 days, we ignore it.

Like a gynecologist reading your most recent signs first.

METHODOLOGY · 05

The 70/30 blend

The algorithm never blindly follows a single signal. The final prediction is 70 % your recent signals + 30 % your average.

This anchor prevents drift: one misread signal can't pull you far from your reality.

METHODOLOGY · 06

And if there's a doubt?

If Plumm sees signals that contradict each other (an ovulation cue AND a period cue within 3 days), it switches to cautious mode: baseline prediction + low confidence. And it tells you why.

A « not sure » beats a false certainty.

METHODOLOGY · 07

The limit, because we have to say it

Plumm is a tracking tool, not a medical device. Even with the best algorithm, predicting ovulation 100 % of the time is impossible — the body isn't a clock.

For contraception, use a real method. To plan a pregnancy, get proper support. With a long delay, abnormal pain or unusual bleeding: see a professional. We walk with you, we don't replace a doctor.

Ready to truly see your cycle?

Free. Let the algorithm learn from you.

Download Plumm