If you have @TheTerminal paste this query into excel, quite cool
=BQL.QUERY("GET(DROPNA(CALENDAR(TYPE=ECONOMIC_RELEASES,SUBTYPE=ALL,VIEW=Standard),REMOVE_ID=1)) FOR('US Country') WITH(DATES=RANGE(2026-01-28,2026-02-28))", "showallcols=true")
If you've used machine learning to solve problems, one of the common questions you will have is how to do feature selection?
One possibility is the Sequential Forward Selection (SFS), which builds a feature subset one feature at a time. However, it is not feasible when working with an enormous set of features AND has issues with path dependency!
In today's article we cover a strictly superior variant of the Sequential Forward Selection!
Find it at the bad place, or retweet for a chance at a free article!
A few other AI prompts I have been using to look at stocks
> Create a summary of recent earnings calls and tell me what management is focused on
> Help me understand historical catalysts behind the stock price. What news or events moved the stock up or down more than 5% in the last 5 years?
> Give me a breakdown of revenue, EBITDA, earnings by segment
> Summarize any KPIs reported by the company and how those KPIs move topline and bottom line
> Give me a detailed background of the executive team and relevant experience they have in the sector
> Break down EBIT, EBITDA and net income margins. Create a table showing side by side margins of comparable companies
Portfolio of a current ~$1 billion fund that has underperformed enormously for 5 years in a row. I'll give brief, honest, 2 minute thoughts on each stock in this thread.
As a PM looking for employment, you should often think about what potential employers want to know from you!
1. Do you provide exposure to an alpha that they lack or wish to scale up from?
2. Can you get to a size that is meaningful to them? For tier 1 hedge funds, 50mn - 100mn is meaningful. For prop shops, even 1mn might be meaningful. This depends on the scale of the prop shop, tiers matter. It will look very different at Tower vs Graviton.
3. How much do you cost? When can you GTM? What is their recoup rate like if things go according to plan? When can you scale to a size that is meaningful?
4. What are the unknowns here? Have you done THIS before? Were you an established PM? Is this your first PM gig? As a researcher, were you involved at all in monetization? Do you know all the data intricacies?