Trendoday

Show HN: I have trained 15 blood glucose forecasting models on my own data

7 comments

  • Points113
  • Comments60
–Rank now
#14Peak rank
5Days on list
79Score · 7d
Nov 10, 2026First seen
Rank · 7 days

On Hacker News

Points
113
Comments
60
Submitted by
0xdeadf1sh
Posted
Nov 10, 2026
Site
github.com

Story details from Hacker News ↗ · linked article on github.com.

Trending history

Show HN: I have trained 15 blood glucose forecasting models on my own data was first seen on Hacker News · Front page on Nov 10, 2026. Since then it has appeared in 126 checks on 5 different days, across 3 lists (Hacker News · Front page, Hacker News · Show HN, Hacker News · Show HN · this week). Its best position was #14 of 30, reached on Nov 14, 09:43 UTC. It dropped off the list after Nov 16, 05:50 UTC.

Rank history

Position on Hacker News · Front page at every check (lower is better).

#1#11#20#30 08:2810:4713:0615:2517:43 Nov 14, 08:28 UTC · #17Nov 14, 08:43 UTC · #15Nov 14, 08:58 UTC · #16Nov 14, 09:13 UTC · #17Nov 14, 09:28 UTC · #16Nov 14, 09:43 UTC · #14Nov 14, 09:58 UTC · #16Nov 14, 10:13 UTC · #17Nov 14, 10:28 UTC · #17Nov 14, 10:43 UTC · #17Nov 14, 10:58 UTC · #18Nov 14, 11:13 UTC · #19Nov 14, 11:28 UTC · #17Nov 14, 11:43 UTC · #20Nov 14, 11:58 UTC · #18Nov 14, 12:13 UTC · #18Nov 14, 12:28 UTC · #18Nov 14, 12:43 UTC · #19Nov 14, 12:58 UTC · #19Nov 14, 13:13 UTC · #19Nov 14, 13:28 UTC · #20Nov 14, 13:43 UTC · #21Nov 14, 13:58 UTC · #21Nov 14, 14:13 UTC · #21Nov 14, 14:28 UTC · #24Nov 14, 14:43 UTC · #26Nov 14, 14:58 UTC · #26Nov 14, 15:13 UTC · #26Nov 14, 15:28 UTC · #24Nov 14, 15:43 UTC · #25Nov 14, 15:58 UTC · #25Nov 14, 16:13 UTC · #25Nov 14, 16:28 UTC · #25Nov 14, 16:43 UTC · #29Nov 14, 17:13 UTC · #29Nov 14, 17:28 UTC · #29Nov 14, 17:43 UTC · #30

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

Platform metric as reported by Hacker News.

0275381 08:2810:4713:0615:2517:43 Nov 14, 08:28 UTC · 20Nov 14, 08:43 UTC · 22Nov 14, 08:58 UTC · 23Nov 14, 09:13 UTC · 26Nov 14, 09:28 UTC · 28Nov 14, 09:43 UTC · 31Nov 14, 09:58 UTC · 34Nov 14, 10:13 UTC · 34Nov 14, 10:28 UTC · 34Nov 14, 10:43 UTC · 36Nov 14, 10:58 UTC · 36Nov 14, 11:13 UTC · 36Nov 14, 11:28 UTC · 38Nov 14, 11:43 UTC · 40Nov 14, 11:58 UTC · 42Nov 14, 12:13 UTC · 43Nov 14, 12:28 UTC · 44Nov 14, 12:43 UTC · 46Nov 14, 12:58 UTC · 47Nov 14, 13:13 UTC · 48Nov 14, 13:28 UTC · 50Nov 14, 13:43 UTC · 51Nov 14, 13:58 UTC · 53Nov 14, 14:13 UTC · 53Nov 14, 14:28 UTC · 55Nov 14, 14:43 UTC · 58Nov 14, 14:58 UTC · 60Nov 14, 15:13 UTC · 63Nov 14, 15:28 UTC · 66Nov 14, 15:43 UTC · 67Nov 14, 15:58 UTC · 69Nov 14, 16:13 UTC · 71Nov 14, 16:28 UTC · 74Nov 14, 16:43 UTC · 75Nov 14, 17:13 UTC · 78Nov 14, 17:28 UTC · 79Nov 14, 17:43 UTC · 81

Where it trended

ListBestDaysChecksLast seen
Hacker News · Front page#14137
Hacker News · Show HN#3246
Hacker News · Show HN · this week#17343

From the discussion

A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.

89% TIR, well done! Cool to see the research, I’m surprised there aren’t more in-depth n=1 studies out there from statistics/data-savvy diabetics. I built a small dashboard exactly collating carb, insulin, sleep, and movement data and trying to coax out useful correlations to help manage. Some interesting insights,…

Looks like gradient boosted trees did really well! XGBoost and LightGBM took the top two spots on average error, doing better than the more computationally expensive transformer models. They did weaker on low-glucose detection, which is pretty bad in this particular case. But it's possible that's fixable by tweaking…

Incredible work! As a T1D I've been gathering as much data as possible (blood glucose, insulin-on-board, food consumed, heart rate, skin temperature, etc.) for exactly this purpose. Can't wait to dive in! BG forecasting and insulin response has always seemed to me to be such a personal thing (everyone has such a…

Questions

Is Show HN: I have trained 15 blood glucose forecasting models on my own data trending on Hacker News right now?

Not at the moment. It was last on the list on Nov 16, 05:50 UTC, after 5 days of trending.

What is the highest rank Show HN: I have trained 15 blood glucose forecasting models on my own data reached?

#14 on Hacker News · Front page, on Nov 14, 09:43 UTC. Trendoday checks this list every 15 minutes.

How long has Show HN: I have trained 15 blood glucose forecasting models on my own data been trending?

It was first seen on Nov 10, 2026 and has been on the list on 5 days (126 checks) since.

How much discussion did it get on Hacker News?

113 points and 60 comments; submitted by 0xdeadf1sh on Nov 10, 2026.