just posted: "Advertising is an Emergent Property of Successful Platforms" Short and sweet. With @dade_us platformpapers.substack.com/p/advertisin...

Day 2 videos posted: 2025 Workshop on Platform Analytics www.youtube.com/playlist?lis...

We just posted Workshop on Platform Analytics Day 1 talk videos! www.youtube.com/watch?v=OlBp...

natural experiment alert couponsinthenews.com/2025/03/24/c...

We're looking forward to another great Workshop on Platform Analytics in San Diego! Registrations close March 23. platformanalytics.org

This is an *amazing* IO conference coming up end of May, organized by @guenter-hitsch.bsky.social, Ali Hortaçsu, @sanjog.bsky.social, and Chad Syverson: econincubator.uchicago.edu/events/indus...

Replacing "I hope this email finds you well" with "Failure to respond will be taken as a resignation." in all emails from now on.

"The bottom 80% of earners spent 25% more than they did four years earlier, barely outpacing price increases of 21% over that period. The top 10% spent 58% more." www.wsj.com/economy/cons...

... ... did you know the US government has a dad joke website? www.fatherhood.gov/for-dads/dad...

More people building alternatives on ATprotocol is important! It helps protect against enshittification and an evil takeover. Exciting to see more people embrace an "I can build it" approach. Also this is why open protocols are so important.

Program posted: 2025 Workshop on Platform Analytics platformanalytics.org

New paper with @adam-n-smith.bsky.social papers.ssrn.com/sol3/papers.... Our paper develops a new approach for estimating demand nonparametrically while imposing economic constraints and comes with a new package, NPDemand.jl! Some things we do in the paper 1/

🚨Closing out 2024 with a new paper with @hristakeva.bsky.social and @leofeler.com: How GLP-1 medications like Ozempic are reshaping food demand and changing the rules of the game for the food industry.

Natural confounded experiment alert. www.cbsnews.com/news/tiktok-...

It's a good time to mention that Seth Benzell and I have a podcast called Justified Posteriors discussing the economics of AI and other technologies. Our latest episode considers @timobres.bsky.social's paper on AI and Aggregate Growth. empiricrafting.substack.com/p/beyond-tas...

Remarkable context here.

natural experiment alert www.mass.gov/news/ag-camp...

Honey’s deal-hunting browser extension is accused of ripping off customers and YouTubers - https://www.theverge.com/2024/12/23/24328268/honey-coupon-code-browser-extension-scam-influencers-affiliate-marketing

This is a remarkable paper www.steven-hamilton.com/s/241208_100... Especially if you're interested in consumption, financial management and heterogeneity.

There are so many types of identity signals it can be hard to keep track (see what I did there, LOL). Our latest in depth explainer: "Identity Signals Explained" www.adtechexplained.com/p/identity-s...

🚨📜CALL FOR PAPERS 📜🚨 *New Data for Consumer Insights Conference* When: May 30-31, 2025 Where: Chicago Booth Submission Deadline: Jan 6, 2025 Keynotes: @susanathey.bsky.social and Greg Lewis Both methodological and empirical submissions are welcome. Submit here: ndconference2025.hotcrp.com

Natural experiment alert www.france24.com/en/live-news...

Field Experiments have matured from academic curiosity to bona fide contributor to knowledge in the past few decades. Yet, the political economy of their deployment in government remains ill-understood. We provide insights in a new working paper, available here: ideas.repec.org/p/feb/natura...

Advertising is an emergent property of successful platforms. techcrunch.com/2024/12/05/b...

Very cool to see my research with Poet Larsen and Davide Proserpio cited in this week's Economist. www.economist.com/briefing/202...

there's a lot of bots on here.

Advertising is an emergent property of successful platforms. www.ft.com/content/9350... archive.is/Zoc3n

I wonder if rejecting amazon prime on every transaction hardens consumer refusals. Do expected returns go negative after say 100+ offer rejections? Curious if amzn tested with long-term metrics, or if reanalysis of initial experiments would reveal. Ofc, cart abandonment is the obvious downside.

“If anything has changed about my reading over the years, it is that I value the state a book puts me in more than I value the specific contents” lithub.com/in-praise-of...

Most misinformation is funded by advertising. Most advertisers who fund misinformation don't realize where their ad dollars go. When they learn the truth, they stop funding misinformation. Sunlight is the best disinfectant. Link in next post

A hundred years after Hotelling, researchers in Northern India hatched the Restauranting Model.

An empirical econ paper needs two things: 738 robustness checks concluding we can’t really ever fully be sure of internal validity in the appendix, and one (1) wild back of the envelope calculation indicating that the result is world-changing in the discussion section

About WoPA submissions. We ask authors not to submit papers that are accepted or invited for revision. PC will screen for this. We hope the workshop enables productive feedback. Authors of invited revisions focus primarily on review team feedback, not workshop feedback. platformanalytics.org

At its core, it is the ultimate conflict of interest. Someone with a personal financial incentive is searching for a measurement tool to tell them that their media is working. According to [insert vendor] we delivered [insert KPI]. Now pay me my bonus. Measurement companies line up to serve.

Is attribution really as messy as people make it out to be? Or is everyone being dramatic?

I'm writing up a brief history of the tidyverse? What do you want to know about it? #rstats

Cat pic >>> earnest self introduction

🛠️ What we did: We built a browser extension that intercepts users’ social media feeds, uses GPT to identify polarizing content in real time, and re-ranks posts to change their visibility. We do this without impacting the user experience. Read more about the tool: arxiv.org/abs/2406.19571

I'm starting a fantasy social science department League. One point for each Google scholar citation, 100 points for each major publication. You can start two full professors, two associate professors, two assistant professors and four doctoral students. Each matchup lasts 20 years

Here are some nice mushrooms

I can retire now

This is my favorite account on all socials and I'm not entirely sure what that says about me

go.bsky.app/NHpEu1g Is there one already? Please message me to be added

We wrote a draft handbook chapter on using algorithmic pricing to learn optimal platform fees. A challenging and interesting problem! Comments welcome. papers.ssrn.com/sol3/papers.... With the great Kanishka Misra (BC)

Validated Facebook's calm, non-interruptive ad format. The presenter I saw said he did not expect similar effects for more interruptive ads like YouTube. So "online ads" in the title is broader than the evidence. Picking nits in case any bsky scrollers neglect to read the entire paper..

I would even add: please shamelessly promote your work One terrific thing I enjoyed on old Twitter was discovering new papers Trust me, you will have an audience if you share your work on Bluesky

The bar has risen so much. My jmp was half finished and the only paper I had.

Good overview of current bluesky ecosystem for technically minded people. Imo the best bet for long term usage, but there arel important platform design choices yet to be made. anderegg.ca/2024/11/15/m...

It is so incredibly nice to have a social platform that values links again - a breath of fresh air in the poisoned ecosystem of the creator economy

Calling CMO’s, VPs of Marketing and comms teams! If you want to be added please comment below go.bsky.app/KCx3iN2