back
user profile
brandonb
9,324karma·1,335submissions·January 17, 2011
about
Data for good.
Co-Founder at Empirical Health (https://empirical.health). Don't die of heart disease.
Before: Co-Founder @ Cardiogram (ML for heart health)
CTO at Sift Science (YC S11, machine learning to fight fraud)
Data Science @ UCSF Cardiology
HealthCare.gov rescue team
Google (Android speech recognition, search ads ML)
brandonb.cc
recent activity (1,335 total)
comment
I think the VC's funding decision is definitely based on growth potential, and less on need for money, but both New Enterprise and Old Enterprise startups tend to require a lot of money to scale …
comment
Pricing is such a black art! Unfortunately it's not something you can easily A/B test. My general advice on pricing is to try to make it a "no-brainer." One way to do that is quant…
comment
The way the site is written, it definitely looks like New Enterprise. But to figure out what the right model is, I'd want to understand how your customers prefer to buy the software. So far, are …
comment
I'm the OP, happy to answer any questions or chat with any B2B startup founders out there!
comment
I didn't interpret it as "you are stupid." It's actually surprisingly common for first-time founders, even smart ones, to have terrible startup ideas. It takes time to develop good…
comment
(I don't like advertising on these threads, but since somebody asked me directly I'll reply.) Credit card companies protect consumers, but not merchants. When you call up your bank to report…
comment
Do you think it's bad because you disagree with the point of the Linus reference, or because you didn't understand it without context?
comment
Yep. That's it.
comment
Very true. The customers that were the biggest pain in the ass also provide the most accurate, detailed feedback. But it can be hard to hear when you've been up 20 hours working on something. You…
comment
This was two years ago, and so far PG's advice is turning out well: we were able to raise a seed round, series A, get a bunch of customers, and hire an awesome team. You can never be exactly sure…
comment
The Firebase team is amazing, congrats to them!
comment
A lot of people who apply mention that they enjoyed the small puzzle. It's not intended to take much time -- if it's not clear after a few minutes, feel free to just email jobs@siftscience.com.
comment
Sift Science
San Francisco, CA - FULLTIME or INTERN Sift Science fights fraud with machine learning, recently raised a series A, and launched two weeks ago:
http://www.wired.com/wiredenterprise/20…
comment
Our customers send examples of users that they've banned from their site or who have caused a credit card chargeback -- these are the $label events in our API and quickstart. Those $label events let u…
comment
Great question. We should add it to a FAQ. The PCI-DSS rules apply to systems that store the entire credit card number ("PAN" in PCI-DSS parlance). We don't accept the full credit card number -- just …
comment
(I work at Sift Science.) One thing to note -- our system analyzes a whole bunch of patterns for each user. So just shopping at 3am by itself won't cause problems, nor will using a prepaid gift card b…
comment
(I work at Sift Science.) We provide a score, and then let our customers decide what to do. The majority of our customers have a human review the user, and sometimes as part of that review, they'll do…
comment
(I work at Sift Science.) For what it's worth, you can score up to 5000 users per month completely free with Sift Science. So if you run a small site, there's no fee. If you run a large site, you can …
comment
Yeah, absolutely! You can train our system to detect whatever type of bad behavior you care most about by giving previous examples of bad users you've banned from the site. Some of our customers have …
comment
You're right on. In theory, you could train our system to recognize good behavior if you sent us enough $label events, but most of the patterns we have today are really optimized around detecting bad …
comment
The two biggest anti-fraud vendors are Accertify and ReD. You might also look at ThreatMetrix, 41st Parameter, and Iovation, who do primarily device identification. Let us know what you think!
comment
Definitely! What would be your top choices? And what's your ideal integration experience?
comment
Hey Devon -- thanks for the thoughtful comments! Most of our customers do use Sift Science for financial fraud, but because it's a machine learning system, you can train it to detect other types of ba…
comment
That's a small puzzle. :)