Kurtosis Conjecture for Decision Trees скачать в хорошем качестве

Kurtosis Conjecture for Decision Trees

The goal of this paper is to propose a method for determining over and under fitted models. Decision trees are the main topic of this paper however the idea seems to be more general to all model types. This is not a mathematical or scientific proof. This paper expresses the idea of how to determine over and under fitting of a model based on the kurtosis of the residuals and more theoretically the amount of true information being extracted by a model from data based on anecdotal industry experience. I challenge those reading this paper to test the idea and provide feedback on their discoveries. Download paper here: https://papers.ssrn.com/sol3/papers.c... Connect with me:   / dimitri-bianco     / dimitribianco   Website: https://www.FancyQuantNation.com Discord:   / discord   Support the channel: https://ko-fi.com/fancyquant Quant t-shirts, mugs, and hoodies: https://www.teespring.com/stores/fanc...