METHOD FOR SCREENING SAMPLES FOR BUILDING PREDICTION MODEL AND COMPUTER PROGRAM PRODUCT THEREOF

Fan-Tien Cheng (Inventor)

Research output: Patent

Abstract

A method for screening samples for building a prediction model and a computer program product thereof are provided. When a set of new sample data is added to a dynamic moving window (DMW), a clustering step is performed with respect to all of the sets of sample data within the window for grouping the sets of sample data with similar properties as one group. If the number of the sets of sample data in the largest group is greater than a predetermined threshold, it means that there are too many sets of sample data with similar properties in the largest group, and the oldest sample data in the largest group can be deleted; if smaller than or equal to a predetermined threshold, it means that the sample data in the largest group are quite unique, and should be kept for building or refreshing the prediction model.
Original languageEnglish
Patent number8862525
Publication statusPublished - 2013 Jun 20

Fingerprint

Prediction Model
Screening
Grouping
Clustering

Cite this

@misc{dbb38b9763d64dfc98a1c15cc0b51304,
title = "METHOD FOR SCREENING SAMPLES FOR BUILDING PREDICTION MODEL AND COMPUTER PROGRAM PRODUCT THEREOF",
abstract = "A method for screening samples for building a prediction model and a computer program product thereof are provided. When a set of new sample data is added to a dynamic moving window (DMW), a clustering step is performed with respect to all of the sets of sample data within the window for grouping the sets of sample data with similar properties as one group. If the number of the sets of sample data in the largest group is greater than a predetermined threshold, it means that there are too many sets of sample data with similar properties in the largest group, and the oldest sample data in the largest group can be deleted; if smaller than or equal to a predetermined threshold, it means that the sample data in the largest group are quite unique, and should be kept for building or refreshing the prediction model.",
author = "Fan-Tien Cheng",
year = "2013",
month = "6",
day = "20",
language = "English",
type = "Patent",
note = "8862525",

}

TY - PAT

T1 - METHOD FOR SCREENING SAMPLES FOR BUILDING PREDICTION MODEL AND COMPUTER PROGRAM PRODUCT THEREOF

AU - Cheng, Fan-Tien

PY - 2013/6/20

Y1 - 2013/6/20

N2 - A method for screening samples for building a prediction model and a computer program product thereof are provided. When a set of new sample data is added to a dynamic moving window (DMW), a clustering step is performed with respect to all of the sets of sample data within the window for grouping the sets of sample data with similar properties as one group. If the number of the sets of sample data in the largest group is greater than a predetermined threshold, it means that there are too many sets of sample data with similar properties in the largest group, and the oldest sample data in the largest group can be deleted; if smaller than or equal to a predetermined threshold, it means that the sample data in the largest group are quite unique, and should be kept for building or refreshing the prediction model.

AB - A method for screening samples for building a prediction model and a computer program product thereof are provided. When a set of new sample data is added to a dynamic moving window (DMW), a clustering step is performed with respect to all of the sets of sample data within the window for grouping the sets of sample data with similar properties as one group. If the number of the sets of sample data in the largest group is greater than a predetermined threshold, it means that there are too many sets of sample data with similar properties in the largest group, and the oldest sample data in the largest group can be deleted; if smaller than or equal to a predetermined threshold, it means that the sample data in the largest group are quite unique, and should be kept for building or refreshing the prediction model.

M3 - Patent

M1 - 8862525

ER -