Scoring model construction method based on logistic regression and rules

One or more embodiments of the invention provide a scoring model construction method based on logistic regression and rules. The method comprises the following steps: screening to obtain rule scoring indexes; constructing a logistic regression scoring card model by using other scoring indexes except...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	HAN CHUANZAN, LI RONGHUA, FU FANGJI
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	CALCULATING COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	One or more embodiments of the invention provide a scoring model construction method based on logistic regression and rules. The method comprises the following steps: screening to obtain rule scoring indexes; constructing a logistic regression scoring card model by using other scoring indexes except the rule scoring index; obtaining a scoring rule of the rule scoring index; according to a scoring rule, obtaining a rule score of the rule scoring index; according to the rule scores, AR values of all the rule scoring indexes are calculated, and the rule scoring indexes are sorted according to the AR values; and according to the logistic regression score card model and the rule scores, training the rule scoring indexes according to the sequence to obtain a scoring model. According to the method, the rule model is integrated into the logistic regression scoring card model, so that the influence of the scoring index which is low in occurrence frequency but has relatively high risk once being triggered on the scorin