सभी किताबें

पेशेवर

ऐप्स परिचय Coach लॉग इन पढ़ना शुरू करें

Quantitative Finance · शब्दावली

Sequential bootstrap क्या है?

Definition 2.7 Machine Learning for Markets · अध्याय 2 — Targets, Labels and Sample Weights

The sequential bootstrap draws labels one at a time, with replacement, each with probability proportional to the average uniqueness it would have given the labels already drawn; overlapping labels become less likely once one of them is in the sample.

bootstrap samplesmarket 1market 2market 3mean
plain, full size0.5040.5170.5090.510
average-uniqueness size0.5110.5120.5060.510
same, weighted by uniqueness0.5060.5110.5100.509
Table 2.1. Out-of-sample AUC of 30 bagged trees predicting the sign of the ten-day return, trained on the first 60% of the dates (purged) of three simulated markets. Data: ml_labels.bagging_table.
अध्याय में पढ़ें →