Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Time Series Forecasting with Graph Transformers

kumo.ai

Post reply on HN
Print view View original

11–20 of 43 posts

Re: Time Series Forecasting with Graph Transformers

#11

Post by tech_ken »

loehnsberg wrote: post #5

[flagged]

This is sales research, and after "CAGR in a GSheet" FB Prophet is what's going to be most recognizable to the widest base of customers.

FWIW seems like the real value add is this relational DB model: https://kumo.ai/research/relational-deep-learning-rdl/ The time-series stuff is them just elaborating the basic model structure a little more to account for time-dependence

Re: Time Series Forecasting with Graph Transformers

#12

Post by almosthere »

pealco wrote: post #4
ziofill wrote: post #2

I can't stand websites that override scrolling

Most of my time interacting with this site was spent in developer tools, trying to figure out where the scrolling behavior was coming from. (Couldn't figure it out.) I can't understand why people are still doing this in 2025.

Most likely the developer is using a Windows computer.

Re: Time Series Forecasting with Graph Transformers

#14

Post by bestest »

pealco wrote: post #4
ziofill wrote: post #2

I can't stand websites that override scrolling

Most of my time interacting with this site was spent in developer tools, trying to figure out where the scrolling behavior was coming from. (Couldn't figure it out.) I can't understand why people are still doing this in 2025.

Enter this in the console:

document.body.onwheel = (e) => e.stopPropagation();

Re: Time Series Forecasting with Graph Transformers

#17

Post by loehnsberg »

esafak wrote: post #7
loehnsberg wrote: post #5

[flagged]

Why? That is what everybody uses. What do you use?

L1-regularized autoregressive features, holiday dummies, Fourier terms (if suitable in combination) yield lower test errors, are faster in training, and easier to cross-validate than Prophet.

Re: Time Series Forecasting with Graph Transformers

#19

Post by esafak »

loehnsberg wrote: post #17
esafak wrote: post #7

Earlier quoted context omitted.

Why? That is what everybody uses. What do you use?

L1-regularized autoregressive features, holiday dummies, Fourier terms (if suitable in combination) yield lower test errors, are faster in training, and easier to cross-validate than Prophet.

With which library though? Is it fast enough for production?

Re: Time Series Forecasting with Graph Transformers

#20

Post by tech_ken »

meindnoch wrote: post #18

[flagged]

> If this really worked, you'd be making billions on the stock market

That's kind of a weird thing to say given that the market cap for quantitative finance is well over a billion dollars, and this product clearly seems to be targeting that sector (plus others) as a B2B service provider. Do you think that all those quantitative trading firms are using something other than time-series analytics?

Also, setting aside the issue of whether time-series forecasting is valuable for stock-market trading, it seems like the value add of this product isn't necessarily the improved accuracy of the forecasts, but rather the streamlined ETL -> Feature Engineering -> Model Design process. For most firms (either in quantitative finance or elsewhere) that's the work of a small dedicated team of highly-trained specialists. This seems like it has the potential to greatly reduce the labor requirements for such an organization without a concomitant loss of product quality.

Post reply on HN