Ben Draves
@bendraves.bsky.social
ML Scientist @Uber in🗽🚕
Working on RecSys /CausalML 📈🪄
PhD Stats. BS in Math. 👨💻📚
Running long distances, reading long books.
Find me here dravesb.github.io
Working on RecSys /CausalML 📈🪄
PhD Stats. BS in Math. 👨💻📚
Running long distances, reading long books.
Find me here dravesb.github.io
Pinned
Ben Draves
@bendraves.bsky.social
· Nov 16
Benjamin Draves
dravesb.github.io
Hey folks👋
My name is Ben and I’m a Data Scientist at Uber working on RecSys and CausalML. I’m a proud statistician with interests in matrix analysis and graph inference.
I live in NYC where I enjoy running long distances and reading a bit of everything. Find me here dravesb.github.io!
My name is Ben and I’m a Data Scientist at Uber working on RecSys and CausalML. I’m a proud statistician with interests in matrix analysis and graph inference.
I live in NYC where I enjoy running long distances and reading a bit of everything. Find me here dravesb.github.io!
When I first learned about RAG, I couldn’t believe it was just “ “.join(docs)
It does feel like
RAG -> Variable Selection
CoT -> Boosting
sure there are others too…
It does feel like
RAG -> Variable Selection
CoT -> Boosting
sure there are others too…
December 30, 2024 at 4:00 PM
When I first learned about RAG, I couldn’t believe it was just “ “.join(docs)
It does feel like
RAG -> Variable Selection
CoT -> Boosting
sure there are others too…
It does feel like
RAG -> Variable Selection
CoT -> Boosting
sure there are others too…
It also - for me at least - takes the joy out of it. Science is a participatory discipline and “playing the game” makes “scoring the points” all the more enticing (especially for kids!)
December 24, 2024 at 10:27 PM
It also - for me at least - takes the joy out of it. Science is a participatory discipline and “playing the game” makes “scoring the points” all the more enticing (especially for kids!)
What app are folks using for e-readers these days? I’m a physical book + digital notes guy but the confines of my Manhattan apartment is causing me to start buying digital - any recommendations?
December 22, 2024 at 9:08 PM
What app are folks using for e-readers these days? I’m a physical book + digital notes guy but the confines of my Manhattan apartment is causing me to start buying digital - any recommendations?
I get mad about this once a week. Just terrible brand positioning
December 14, 2024 at 2:50 AM
I get mad about this once a week. Just terrible brand positioning
So locked in open.spotify.com/track/11AEDk...
Christmas Miracle
Dimension 32, Quantum Break · Lofi Girl - Christmas 2024 · Song · 2024
open.spotify.com
December 10, 2024 at 3:27 PM
So locked in open.spotify.com/track/11AEDk...
Wait, no he’s right
December 6, 2024 at 2:41 PM
Wait, no he’s right
Oh no - didn’t mean to scoop any takes from the bad place 😅
December 4, 2024 at 2:04 PM
Oh no - didn’t mean to scoop any takes from the bad place 😅
The most impactful CRM personalization is
select user, song, count(*)
from plays
group by 1, 2
order by 3 desc
Always has been. Always will be.
select user, song, count(*)
from plays
group by 1, 2
order by 3 desc
Always has been. Always will be.
December 4, 2024 at 1:58 PM
The most impactful CRM personalization is
select user, song, count(*)
from plays
group by 1, 2
order by 3 desc
Always has been. Always will be.
select user, song, count(*)
from plays
group by 1, 2
order by 3 desc
Always has been. Always will be.
I’ve been implementing some time series type estimates at work this week and man oh man the indexing / naming conventions have me 😵💫😵💫😵💫
December 3, 2024 at 4:24 PM
I’ve been implementing some time series type estimates at work this week and man oh man the indexing / naming conventions have me 😵💫😵💫😵💫
Reposted by Ben Draves
Got an email, "Thank you for coverage․py." I immediately thought, "they're going to want something, or complain about something."
Nope! It was all positive. Ended with "Thanks again for this awesome Python contribution!"
If you like what someone has done, tell them!
Nope! It was all positive. Ended with "Thanks again for this awesome Python contribution!"
If you like what someone has done, tell them!
December 2, 2024 at 3:07 PM
Got an email, "Thank you for coverage․py." I immediately thought, "they're going to want something, or complain about something."
Nope! It was all positive. Ended with "Thanks again for this awesome Python contribution!"
If you like what someone has done, tell them!
Nope! It was all positive. Ended with "Thanks again for this awesome Python contribution!"
If you like what someone has done, tell them!
Getting a new laptop Monday - so excited to set up everything “right” this time only for it to explode immediately.
December 1, 2024 at 4:01 PM
Getting a new laptop Monday - so excited to set up everything “right” this time only for it to explode immediately.
Yeah something beautiful about a NYC bar on Saturday morning with first round coffees, second round are beers
November 30, 2024 at 7:38 PM
Yeah something beautiful about a NYC bar on Saturday morning with first round coffees, second round are beers
It’s also a religious tradition at this point
November 30, 2024 at 7:06 PM
It’s also a religious tradition at this point
I was agonizing over why our SPR performance took a nose dive last week. Spent times in the logs, staring at feature values, investigating the FPR.
The front end was using rankings[::-1] not rankings 🙃 Sometimes the 10x work is not trusting a thing that comes out of the API.
The front end was using rankings[::-1] not rankings 🙃 Sometimes the 10x work is not trusting a thing that comes out of the API.
November 26, 2024 at 12:29 AM
I was agonizing over why our SPR performance took a nose dive last week. Spent times in the logs, staring at feature values, investigating the FPR.
The front end was using rankings[::-1] not rankings 🙃 Sometimes the 10x work is not trusting a thing that comes out of the API.
The front end was using rankings[::-1] not rankings 🙃 Sometimes the 10x work is not trusting a thing that comes out of the API.
One of my big ah-ha moments was “wait… the hidden layers are just doing feature engineering”.
November 21, 2024 at 4:06 PM
One of my big ah-ha moments was “wait… the hidden layers are just doing feature engineering”.
I forgot how nice it is to open an app and be flooded with cool ML/Stats-y stuff. Bluesky has big happy hour at a conference vibes and it’s 👌
November 19, 2024 at 11:43 PM
I forgot how nice it is to open an app and be flooded with cool ML/Stats-y stuff. Bluesky has big happy hour at a conference vibes and it’s 👌
I regularly send marketers this picture which I feel like is the right level of passive-aggressive grump for this group
November 18, 2024 at 10:29 PM
I regularly send marketers this picture which I feel like is the right level of passive-aggressive grump for this group
Reposted by Ben Draves
I made one for stats papers
November 18, 2024 at 4:02 AM
I made one for stats papers
We really have known the ramifications of RecSys tech (especially in news) all along. It's just that consumers and companies wanted it more than a non-personalized alternative.
What we want vs what is good for us can oftentimes be two different things.
What we want vs what is good for us can oftentimes be two different things.
November 17, 2024 at 6:11 PM
We really have known the ramifications of RecSys tech (especially in news) all along. It's just that consumers and companies wanted it more than a non-personalized alternative.
What we want vs what is good for us can oftentimes be two different things.
What we want vs what is good for us can oftentimes be two different things.
Quote was from 30 years ago...
With GroupLens, users may choose to read articles only from a small group with whom they share many common interests. Over time this could lead to a fracture of the global village into many small tribes, each forming a ... community ... isolated from each other.
With GroupLens, users may choose to read articles only from a small group with whom they share many common interests. Over time this could lead to a fracture of the global village into many small tribes, each forming a ... community ... isolated from each other.
November 17, 2024 at 6:08 PM
Quote was from 30 years ago...
With GroupLens, users may choose to read articles only from a small group with whom they share many common interests. Over time this could lead to a fracture of the global village into many small tribes, each forming a ... community ... isolated from each other.
With GroupLens, users may choose to read articles only from a small group with whom they share many common interests. Over time this could lead to a fracture of the global village into many small tribes, each forming a ... community ... isolated from each other.
Forget ggplot vs base R graphics. Bring back terminal renderings and clip art.
November 16, 2024 at 10:52 PM
Forget ggplot vs base R graphics. Bring back terminal renderings and clip art.
I’m revisiting some original RecSys papers in prep for a new team-member joining and the figures in the original GroupLens paper are just so 🔥
dl.acm.org/doi/10.1145/...
dl.acm.org/doi/10.1145/...
November 16, 2024 at 10:49 PM
I’m revisiting some original RecSys papers in prep for a new team-member joining and the figures in the original GroupLens paper are just so 🔥
dl.acm.org/doi/10.1145/...
dl.acm.org/doi/10.1145/...