Victor Jose's Avatar

Victor Jose

@vrjose.bsky.social

Professor at Georgetown McDonough. Operations and Analytics. Usually thinking about Management Science, Decision Analysis, Data Analytics, JDM, and Applied Statistics. #orms #analytics #datascience #decisionanalysis #forecasting πŸ“Washington, DC

141 Followers  |  250 Following  |  14 Posts  |  Joined: 16.11.2024  |  1.9795

Latest posts by vrjose.bsky.social on Bluesky

This reminds me of how I was intrigued by swarm intelligence when I had to do a project related to ACO (ant colony optimization) as an undergrad (some time ago πŸ˜…) …

26.03.2025 04:34 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Was watching the movie clip of the ants solving the puzzle in the PNAS paper and it was just astounding. 🀯

youtu.be/ZNLtl6KdC34

26.03.2025 04:28 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Happy (1+2+3+4+5+6+7+8+9)^2

01.01.2025 12:26 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Galton's figure plotting the height of children vs. the average height of their parents, titled "Rate of regression in hereditary stature"

Galton's figure plotting the height of children vs. the average height of their parents, titled "Rate of regression in hereditary stature"

Post image Two photos of Francis Galton, left: in profile; right: full face. These were related to Galtn's studies of criminality, now standard in police procedure.

Two photos of Francis Galton, left: in profile; right: full face. These were related to Galtn's studies of criminality, now standard in police procedure.

#TodayinHistory #dataviz #Onthisday #OTD πŸ“Š
πŸ“…Dec 20, 1888 Francis Galton presented his paper on correlation to the Royal Society of London [Stigler:1986,p297]
The fact that the slope here <1 became the rationale for "regression to the mean"

21.12.2024 02:27 β€” πŸ‘ 11    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0

I guess to have some semblance of legitimacy, they have to engage with the scientific review process. I do have some concerns about these new megalithic publishers and what their effect is on science. It becomes harder to separate out which studies and results are rigorous and legitimate.

14.12.2024 14:47 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Last stretch for the fall semester. It’s that feeling when you are running code and know it’s almost done but you are just staring at your screen and waiting.

11.12.2024 12:31 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image Post image Post image Post image

This looks like an amazing project.

Scholars at UMichigan recently collected a massive dataset of over 1.1M podcast transcripts largely comprehensive of all English podcasts.

Using this data, they conduct an investigation into the content, structure, and responsiveness of the podcast ecosystem.

07.12.2024 01:48 β€” πŸ‘ 55    πŸ” 16    πŸ’¬ 3    πŸ“Œ 2
Preview
Google Introduces A.I. Agent That Aces 15-Day Weather Forecasts GenCast, from the company’s DeepMind division, outperformed the world’s best predictions of deadly storms as well as everyday weather.

A new A.I. tool from DeepMind, a Google company in London that develops A.I. applications, has achieved what its makers call unmatched skill and speed in devising 15-day weather forecasts.

04.12.2024 22:56 β€” πŸ‘ 458    πŸ” 95    πŸ’¬ 36    πŸ“Œ 23
Post image

LOL: just got this autogenerated email from Econometrica telling me why I should send my work there. I agree you should totally accept my papers when I send them to you @ecmaeditors.bsky.social πŸ˜‚πŸ˜‚πŸ˜‚

04.12.2024 15:24 β€” πŸ‘ 22    πŸ” 2    πŸ’¬ 2    πŸ“Œ 0
Post image Post image Post image Post image

Can you guess what happens when a Walmart Supercenter enters a community?
...
...
...

β—ΎEITC receipts in the community increase
β—Ύ workers' incomes go down

as a direct result.

"Walmart Supercenters gradually accumulate and exercise monopsony power, with negative consequences for workers."

01.12.2024 03:26 β€” πŸ‘ 246    πŸ” 97    πŸ’¬ 6    πŸ“Œ 11

For those who plan what to do with leftovers before actually creating the leftovers. It’s like me thinking of what to do with a paper before I finish writing it.

28.11.2024 17:08 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Happy Thanksgiving to those who celebrate in the US and Americans outside the United States!

28.11.2024 13:46 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Another reason to be thankful? It’s good for you | CNN There are easy ways to increase our levels of daily gratitude, and good mental and physical health reasons to do so.

To get in better touch with gratefulness, all you have to do is find easy ways to count blessings more often than, say, over an annual turkey dinner.

28.11.2024 13:10 β€” πŸ‘ 267    πŸ” 48    πŸ’¬ 32    πŸ“Œ 13

I guess some people’s job will become more hectic and more algorithms will be in use.

27.11.2024 23:27 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

This reminded me of my spirograph toy from my childhood.

24.11.2024 04:15 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

Harmonographs

www.johndcook.com/blog/2019/10...

23.11.2024 22:09 β€” πŸ‘ 9    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0

This is an amazing starter pack for anyone interested in Decision Science. #starterpack #decisionscience

go.bsky.app/8nDKmwG

23.11.2024 17:01 β€” πŸ‘ 20    πŸ” 4    πŸ’¬ 1    πŸ“Œ 0
Post image Post image Post image Post image

AI can help learning... when it isn't a crutch.

There are now multiple controlled experiments showing that students who use AI to get answers to problems hurts learning (even though they think they are learning), but that students who use well-promoted LLMs as a tutor perform better on tests.

23.11.2024 02:29 β€” πŸ‘ 203    πŸ” 34    πŸ’¬ 12    πŸ“Œ 6

Probably one of my go-to charts on explaining the variability of likely and unlikely statements

20.11.2024 03:32 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Not sure but I am guessing that some form of visibility and recognition in the field is needed in addition to publications. I would say organizing prestigious conferences should help in the margin … even at places that rhyme with Dale πŸ˜…

18.11.2024 16:35 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Yes, I think some call it symmetric KL divergence: d(P,Q) = KL(P||Q) + KL(Q||P)

18.11.2024 16:28 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

I guess you can symmetrize it by summing it with KL in the other direction.

I have naively interpreted this KL quirk in my mind that if you care about getting from a point to another, the effort to get there doesn’t have to be the same. If distance mattered, I’d likely choose another metric.

18.11.2024 14:44 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

In Delta, it’s not always in the middle section between bathrooms but there is always some at the back end of the plane. Haven’t seen ice cream yet but I may need to do more long hauls to increase my sample size.

18.11.2024 14:28 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Bluesky Network Analyzer Find accounts that you don't follow (yet) but are followed by lots of accounts that you do follow.

This is a fantastic tool if you’re looking for people with overlapping interests (as judged by networks) to follow:

bsky-follow-finder.theo.io

18.11.2024 02:49 β€” πŸ‘ 153    πŸ” 68    πŸ’¬ 15    πŸ“Œ 9
Comparison of three views of vote shift, or swing, in the US election: using vertical triangles, diagonal arrows, and a choropleth map. Composite: Bloomberg/New York Times/Datawrapper

Comparison of three views of vote shift, or swing, in the US election: using vertical triangles, diagonal arrows, and a choropleth map. Composite: Bloomberg/New York Times/Datawrapper

If you have strong feelings about these three map formats, then you may enjoy the special US election edition of our newsletter The Crunch! πŸ“Š

www.theguardian.com/news/2024/no...

#dataviz #data

15.11.2024 05:13 β€” πŸ‘ 39    πŸ” 5    πŸ’¬ 2    πŸ“Œ 1
Post image

What a chart.
www.economist.com/interactive/...

15.11.2024 12:37 β€” πŸ‘ 3176    πŸ” 1061    πŸ’¬ 85    πŸ“Œ 137
A screenshot from the β€œmatrix cookbook” showing a series of formulas for derivatives of matrix functions (such as the determinant).

A screenshot from the β€œmatrix cookbook” showing a series of formulas for derivatives of matrix functions (such as the determinant).

… everybody ends up doing linear algebra, whether they like it or not.

Among the most useful recipes, special shoutout to matrix derivatives. The one for log-determinant never ceases to amaze me.

16.11.2024 18:37 β€” πŸ‘ 6    πŸ” 2    πŸ’¬ 2    πŸ“Œ 0

If you are in the informs community and looking for some people to follow on bluesky -- this is a great list to *start* with. I am looking forward to connecting with many mutual friends.

16.11.2024 16:31 β€” πŸ‘ 8    πŸ” 3    πŸ’¬ 0    πŸ“Œ 0

@vrjose is following 20 prominent accounts