A Cost of Misclassification Adjustment Approach for Estimating Optimal Cut-Off Point for Classification

Classification is one of the main areas of machine learning, where the target variable is usually categorical with at least two levels. This study focuses on deducing an optimal cut-off point for continuous outcomes (e.g., predicted probabilities) resulting from binary classifiers. To achieve this a...

Full description

Saved in:
Bibliographic Details
Main Authors: O.-A. Ampomah, R. Minkah, G. Kallah-Dagadu, E. N. N. Nortey
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Journal of Probability and Statistics
Online Access:http://dx.doi.org/10.1155/2024/8082372
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850213813940387840
author O.-A. Ampomah
R. Minkah
G. Kallah-Dagadu
E. N. N. Nortey
author_facet O.-A. Ampomah
R. Minkah
G. Kallah-Dagadu
E. N. N. Nortey
author_sort O.-A. Ampomah
collection DOAJ
description Classification is one of the main areas of machine learning, where the target variable is usually categorical with at least two levels. This study focuses on deducing an optimal cut-off point for continuous outcomes (e.g., predicted probabilities) resulting from binary classifiers. To achieve this aim, the study modified univariate discriminant functions by incorporating the error cost of misclassification penalties involved. By doing so, we can systematically shift the cut-off point within its measurement range till the optimal point is obtained. Extensive simulation studies were conducted to investigate the performance of the proposed method in comparison with existing classification methods under the binary logistic and Bayesian quantile regression frameworks. The simulation results indicate that logistic regression models incorporating the proposed method outperform the existing ordinary logistic regression and Bayesian regression models. We illustrate the proposed method with a practical dataset from the finance industry that assesses default status in home equity.
format Article
id doaj-art-877bde2d650d47ef82e86d85f3c54de6
institution OA Journals
issn 1687-9538
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Journal of Probability and Statistics
spelling doaj-art-877bde2d650d47ef82e86d85f3c54de62025-08-20T02:09:04ZengWileyJournal of Probability and Statistics1687-95382024-01-01202410.1155/2024/8082372A Cost of Misclassification Adjustment Approach for Estimating Optimal Cut-Off Point for ClassificationO.-A. Ampomah0R. Minkah1G. Kallah-Dagadu2E. N. N. Nortey3Department of Statistics and Actuarial ScienceDepartment of Statistics and Actuarial ScienceDepartment of Statistics and Actuarial ScienceDepartment of Statistics and Actuarial ScienceClassification is one of the main areas of machine learning, where the target variable is usually categorical with at least two levels. This study focuses on deducing an optimal cut-off point for continuous outcomes (e.g., predicted probabilities) resulting from binary classifiers. To achieve this aim, the study modified univariate discriminant functions by incorporating the error cost of misclassification penalties involved. By doing so, we can systematically shift the cut-off point within its measurement range till the optimal point is obtained. Extensive simulation studies were conducted to investigate the performance of the proposed method in comparison with existing classification methods under the binary logistic and Bayesian quantile regression frameworks. The simulation results indicate that logistic regression models incorporating the proposed method outperform the existing ordinary logistic regression and Bayesian regression models. We illustrate the proposed method with a practical dataset from the finance industry that assesses default status in home equity.http://dx.doi.org/10.1155/2024/8082372
spellingShingle O.-A. Ampomah
R. Minkah
G. Kallah-Dagadu
E. N. N. Nortey
A Cost of Misclassification Adjustment Approach for Estimating Optimal Cut-Off Point for Classification
Journal of Probability and Statistics
title A Cost of Misclassification Adjustment Approach for Estimating Optimal Cut-Off Point for Classification
title_full A Cost of Misclassification Adjustment Approach for Estimating Optimal Cut-Off Point for Classification
title_fullStr A Cost of Misclassification Adjustment Approach for Estimating Optimal Cut-Off Point for Classification
title_full_unstemmed A Cost of Misclassification Adjustment Approach for Estimating Optimal Cut-Off Point for Classification
title_short A Cost of Misclassification Adjustment Approach for Estimating Optimal Cut-Off Point for Classification
title_sort cost of misclassification adjustment approach for estimating optimal cut off point for classification
url http://dx.doi.org/10.1155/2024/8082372
work_keys_str_mv AT oaampomah acostofmisclassificationadjustmentapproachforestimatingoptimalcutoffpointforclassification
AT rminkah acostofmisclassificationadjustmentapproachforestimatingoptimalcutoffpointforclassification
AT gkallahdagadu acostofmisclassificationadjustmentapproachforestimatingoptimalcutoffpointforclassification
AT ennnortey acostofmisclassificationadjustmentapproachforestimatingoptimalcutoffpointforclassification
AT oaampomah costofmisclassificationadjustmentapproachforestimatingoptimalcutoffpointforclassification
AT rminkah costofmisclassificationadjustmentapproachforestimatingoptimalcutoffpointforclassification
AT gkallahdagadu costofmisclassificationadjustmentapproachforestimatingoptimalcutoffpointforclassification
AT ennnortey costofmisclassificationadjustmentapproachforestimatingoptimalcutoffpointforclassification