Related Posts
Additional Posts in Data Analytics & Data Science
New to Fishbowl?
Download the Fishbowl app to
unlock all discussions on Fishbowl.
unlock all discussions on Fishbowl.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Download the Fishbowl app to unlock all discussions on Fishbowl.
Copy and paste embed code on your site

Scan your QR code to download
Fishbowl app on your mobile

My running theory is that 99% of observational analytics can be solved with a Histogram (sometimes on a timeline).
Coach
Yeah snapshot data!
Re: predictive models i find some element of modelling is significantly more effective than basic statistics.
Why? Because stats tend to be observational and only give you the pure probability of occurrence P(A) of some event. That's good for population studies but not good for individual predictions where you want to identify the likelihood of a choice, while the observed pay has some other set of priors... i.e. where you want P(A|B), where B can be heavily nonlinear in its relationship with A.
The real question here is... what do you consider "complex" models? Do you consider XGBoost complex?
Looool AE1 half of them don't know the difference between mean and median.
Coach
This is where your knowledge comes in, which helps your clients to make it less complicated and easier to understand for them