Matt Gershoff

CEO of Conductrics.
Inference is not a Technology.

[Matt Gershoff @mgershoff]

Amusing podcast where @ezraklein plays Larry Gopnik to Mark Epstein's Nachtner
https://t.co/CpsJaWdydd

[Matt Gershoff @mgershoff]

Good fun at #measurecamptoronto talking about Privacy by design and how applying data minimization gets you both K-anonymization AND ability to efficiently construct Gramian matrices for OLS.

[Christopher Berry @cjpberry]

Pure bias reinforcing dopamine right there. @mgershoff summarizes #PrivacybyDesign at #measurecampto

[Matt Gershoff @mgershoff]

Off to London for @MeasureCampLDN
We have a new batch of Conductrics INC Select whiskey from @MilamandGreene over here from Texas and alfajores direct from Buenos Aires as prizes and give aways.

For talks I will do something on Privacy Engineering and AB Testing.

[Matt Gershoff @mgershoff]

@seanjtaylor Yes but you pay for it with the US=>Europe Jet lag

[Matt Gershoff @mgershoff]

@dggoldst Been Solved

[Matt Gershoff @mgershoff]

tl;dl Privacy by design & customer first philosophy, if not two sides of the same coin, are consistent with each other.
Collecting customer data is akin to asking for something. Customer first means asking from customers only when its a GOOD FAITH attempt to enrich THEIR lives.

[Analytics Power Hour @AnalyticsHour]

"Collect everything" is easy to say. It can even be rationalized. Think a little deeper, though, and the dangers of this mindset are pretty easy to surface. That's the topic of our latest episode with @mgershoff! https://t.co/7Tx5FjgN45

[Matt Gershoff @mgershoff]

@danbarker Wow and all just to see the theme song to the the Royle Family performed live.

[Matt Gershoff @mgershoff]

@cjpberry That turns out to be culturally specific - in parts of Europe they use different colors/markers for

[Matt Gershoff @mgershoff]

I had such a great time getting to meet and chat with the Columbus analytics community. Thank you @tgwilson and the team at @cbusdaw for taking personal time to organize such a welcoming event!

[Tim Wilson @tgwilson]

Privacy by design and more with @mgershoff at @cbusdaw !

[Matt Gershoff @mgershoff]

@cjpberry @tgwilson @cbusdaw Gotta get you down to Austin

[Matt Gershoff @mgershoff]

@tgwilson @MilamandGreene We have none of them so no special privileges here 🤣

[Matt Gershoff @mgershoff]

I know people and I still haven't been able to get a bottle from the Wildlife collection. Gotta up my click submit game.
@MilamandGreene
https://t.co/kmAum4i3lj

[Matt Gershoff @mgershoff]

Ride Sharing product idea.
User Setting Toggle for accept/decline "air freshener'.

[Matt Gershoff @mgershoff]

Great. As an extension to her note about effects heterogeneity. I think it is more that contextual bandits/Targeting is unlikely to be valuable unless there is a theory why there should be heterogeneity. If you don't then just run a simple RCT or Epsilon-First bandit.

[Sean J. Taylor @seanjtaylor]

These recent slides from Susan Athey and Guido Imbens at NBER are a great recent review of the most valuable data science methods I'm aware of. They cover tons of ground with lots of pointers.

https://t.co/BEjcLLi2vq

[Matt Gershoff @mgershoff]

@pcastr @tw_killian @RL_Conference Oh dang - its at UMASS? Would have been a good reason to back for a visit.

[Matt Gershoff @mgershoff]

@NandoDF Have fun!

[Matt Gershoff @mgershoff]

Do you mind if I DM you here on X @thegautamkamath ? If not no worries. Was looking for some links/follow up around a quick question on the dual view of the Diff Privacy and Pearson-Neyman Hypth Testing.

[Matt Gershoff @mgershoff]

Love the @thegautamkamath Youtube course on Diff Privacy.

[Matt Gershoff @mgershoff]

Oh! I have to read. I have been thinking informally about this for Tech/Data Science - that methodological preferences etc. are drawn from individuals who are clustered (in part by being socially connected in the valley via a small set of interconnected VCs)

[Misha Teplitskiy | Science of Science @MishaTeplitskiy]

1. https://t.co/PZmrnib3Gf

Meta-analyses combine trials that are presumably *independent*. But social relatedness between researchers --> more similar effect estimates, suggesting dependency via same "school of thought"