Securities margin trading and asset management target customer mining method

Securities margin trading and asset management target customer mining method

The invention discloses a securities margin trading and asset management target customer mining method comprising the following steps: analyzing transaction data in a database; building a training set and a test set for securities margin trading target customers and asset management target customers...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HU JIA, XIA YINGZHE, YU SHIXIN, CHANG KAI, LIN XUESONG, YANG JIE
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:The invention discloses a securities margin trading and asset management target customer mining method comprising the following steps: analyzing transaction data in a database; building a training set and a test set for securities margin trading target customers and asset management target customers respectively; constructing a dependent variable factor, a basic factor and a total derivative factor for the securities margin trading target customers and the asset management target customers respectively; building a prediction model for the securities margin trading target customers and the asset management target customers respectively through use of a random forest algorithm; and testing the securities margin trading target customers and the asset management target customers and analyzing the test results. According to the invention, user-related attributes are extracted from the database and analyzed, a random forest model is established, the problem that the traditional prediction method is of low efficienc