Top all-time · #5086
Sift
Company blog · blog.siftscience.com/blogprogrammingsecurity
Sift is the company blog at blog.siftscience.com, writing about programming and security. Since 2013, 15 different Hacker News readers have linked it 34 times, most often “Large Scale Decision Forests: Lessons Learned”. It is still writing: the last post was on 2026-10-30, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link Sift's post "The Unreasonable Effectiveness of Random Forests", which argues that random forest models are hard to interpret. The comments dispute that point.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Expert insights on payment fraud, account takeover, chargebacks and digital trust from the team behind Sift's fraud prevention platform.
Most-linked posts?
- Large Scale Decision Forests: Lessons Learned2 people · 3 mentions · first linked 2015-08-25
- Best practices for building large React applications2 people · 2 mentions · first linked 2015-05-07
What Hacker News says?
> Why is it an issue to mention someone's nationality? It's not an issue to mention someone's nationality. Intent matters. That is why you don't say "he's just a black murderer from NYC" or "he's just an arab terrorist". > Do you have perhaps have any pre-conceived ideas around that particular nationality? No, it seems that you have. What a lame attempt to spin it around. Funny how you edited your post after people…
Comment linking /2013/global-e-commerce-fraud
on “Dash for iOS is now open source”Submitted Seven habits of highly fraudulent users as a story · 390 points
HN discussionNice post. However, I was kind of surprised to see the author list interpretability as one of the drawbacks of random forests: > Another point that some might find a concern is that random forest models are black boxes that are very hard to interpret. I generally agree that random forests are more difficult to interpret than linear models such as logistic regression, but I think they're still far more interpretable…
Comment linking /blog/2015/large-scale-decision-forests-lessons-learned
on “The Unreasonable Effectiveness of Random Forests”Submitted React JS Best Practices as a story · 252 points
HN discussionSubmitted Why are payment forms so complicated? as a story · 245 points
HN discussionSubmitted d-Threeact: Making d3 and React the Best of Friends as a story · 160 points
HN discussionSubmitted Best practices for building large React applications as a story · 153 points
HN discussionSubmitted Announcing Sift Science: fight fraud with large-scale machine learning as a story · 126 points
HN discussionSubmitted E-commerce Fraud Facts as a story · 77 points
HN discussionSubmitted How Sift Science Rebuilt Its App on React and DropWizard as a story · 73 points
HN discussionSubmitted Fight fraud frugally as a story · 57 points
HN discussionSubmitted How Fraudulent Users Slip Under the Radar as a story · 55 points
HN discussionSubmitted Mobile fraud detection in iOS 7 as a story · 26 points
HN discussionSubmitted D-Threeact: How Sift Science Made D3 and React the Best of Friends as a story · 23 points
HN discussionSubmitted Mobile e-commerce fraud detection as a story · 22 points
HN discussionSubmitted Large Scale Decision Forests: Lessons Learned as a story · 17 points
HN discussionSubmitted Machine Learning for Poets as a story · 17 points
HN discussionSubmitted Migrating from Rails+Marionette to React as a story · 16 points
HN discussionSubmitted Best practices for building large React applications as a story · 14 points
HN discussionSubmitted The (un)usual suspects – global fraud by country as a story · 14 points
HN discussionSubmitted Analysis of online fraud in the U.S as a story · 9 points
HN discussionSubmitted Adventures in Real-World React Performance Debugging as a story · 8 points
HN discussionSubmitted The Fraudiest States in America as a story · 8 points
HN discussionSubmitted Concurrency and at Least Once with the New Kafka Consumer as a story · 6 points
HN discussionSubmitted From Marionette to React as a story · 6 points
HN discussionSubmitted Making React and D3 Play Nice Together as a story · 5 points
HN discussionSubmitted Browser DGAF That You Use React as a story · 4 points
HN discussionSubmitted Crucial Sass Mixins/Placeholders for Responsive Web Design as a story · 4 points
HN discussionSubmitted Data analysis: online fraudsters and typos as a story · 3 points
HN discussionSubmitted Sift Science raises 30M Series C as a story · 2 points
HN discussion
