Prince Grover

In 2017, during my second year at IIMA, I enrolled in an elective course titled "Massive Change: Economics and Finance.”, by an accomplished visiting professor who was also an alum. The class was small and the topic very captivating to me +

@ZakJost interesting experiment.

I'm running an experiment in Open Research, where I document my ideas and progress as I go. I'm currently looking at using transformers on subgraphs for node classification rather than GNNs. There are a number of conceptual advantages. Details: rb.gy/lvb56

Some final context: fighting spam is incredibly *dynamic*. The adversaries, their goals, and tactics evolve constantly – often in response to our work! You can’t build a set of rules to detect spam today, and hope they will still work tomorrow. They will not.

Shocker of a day — admitted 5 patients to liver ICU with alcohol induced liver failure. Disturbingly, ALL had binged on alcohol in the previous 4 weeks. Sadly, only two of them can be saved by a transplant. Weekend bingeing may be worse than regular drinking. Serious risks are: sudden liver failure, seizures, partner harm, criminal behavior, homicide, suicide.

livemint.com/news/india/you… - article with additional context.

If you suddenly see live stream of Elon Musk giving bitcoin price prediction on your YouTube recommendations, you might be seeing a new scam happening these days. The fraudsters are hijacking YouTube accounts of people with large following. youtube.com/watch?v=EFsRw_…

"Fullz", a slang commonly used by fraud criminals. It means a full set of information on a prospective fraud victim, including name, billing address, cc num, ssn, birth date. Fullz is bought and sold online, typically dark web. Impact of #DataBreach.

@vaibhav3131 if anything, scams like these have only increased on this platform.

Starting a monthly newsletter on "AI for Trust, Safety, and Fraud." Stay informed with the latest trends in this field. Newsletter: lnkd.in/eMdc-p5i Signup form to receive the newsletter: eepurl.com/ioJT0E

@Alharbi77000 How do you define complex? There are some e-commerce transaction data in the benchmark but I would be interested to know if those accomplish your needs. If not, what is lacking in terms of complexity you need.

@groverpr4 I have been doing my research on Fraud Detection E-commerce. The hard thing I face is find large datasets for implementation. It’s lack of availability data. I need help finding complex datasets

We have created a Fraud Dataset Benchmark which is a compilation of publicly available datasets catered to fraud detection, comprising a variety of fraud related tasks. The Python based library provides API for easy data loading with standardized splits. arxiv.org/abs/2208.14417

@vaibhav3131 ?

never meet your heroes yes but also never meet the cooks in the cloud kitchen you order from

@vaibhav3131 Came to me from @ZakJost :D

I'm a little far from midlife (I hope), but this is such a good talk overall on life, meaning, regret, etc. Some great thought experiments to ponder and some I already think of from time to time. Thanks for recommending this @groverpr4 podcasts.google.com/?feed=aHR0cHM6…

We’re excited to announce that Kaggle will be sponsoring $500k in awards for outstanding papers and reviewers in the Machine Learning Reproducibility Challenge 2022. kaggle.com/reproducibilit…

Poster Session 4 has a little different distribution with more self supervised and multi-agent coming on the top.

Is someone else too interested in knowing common topics in papers/posters accepted in #NeurIPS2022 ? Pre-trained, fine-tuning, language models, self supervised, gradient descent seem to be common topics in Poster Session 3 after removing obvious stop words.

❤️ Feeling blessed to have had an amazing day volunteering as a group leader for education outreach at #NeurIPS2022. 250 high school students from #NewOrleans, all asking great questions about AI ethics, copyright, and applications. Thank you for organizing, Matt and Jess! 🙏✨

I am in New Orleans this week for #NeurIPS2022. DM me if you want to chat about fraud detection using machine learning or to explore food options nearby.

@elonmusk Actually it has become boring these days, and quite monotonous. I get bored, open Twitter, then get even more bored, and then go back to work.

Usage of Twitter continues to rise. One thing is for sure: it isn’t boring!

@GergelyOrosz A few of my hypothesis are: - many people respect/follow Musk no matter he does and would blindly follow him and believe that he is doing everything right - people hope to learn a lot by working under his leadership

Serious question: outside of outsized, unvested stock on the line or high compensation, why would any software engineer with options consider working at Twitter, going forward? Policies changing overnight and an owner acting visibly hostile towards staff who built Twitter.

@fchollet Mastadon has a lot of steps in account creation and then finding the right people to follow, and then understanding different servers. Hope that a clone comes quickly, that is easy to onboard to, has interesting feed from day 1, and people find it interesting enough to switch.

@fchollet waiting for it

Twitter is ripe for disruption. But for most people, Mastodon is clearly not the answer. Given how salient the opportunity is, I assume multiple startups must be booting up a Twitter clone right now.