CATEGORICAL FEATURE SELECTION FOR RANKING MODELS

Machine Learning based ranking models are ubiquitous in powering recommendation engines at internet companies. These models typically use a combination of real-valued numerical and categorical features to generate predictions. Feature selection may be a widely encountered problem in this setting, th...

Full description

Saved in:
Bibliographic Details
Main Authors Tripathi, Pushkar, Timmaraju, Aditya Srinivas
Format Patent
LanguageEnglish
Published 27.04.2023
Subjects
CALCULATING
COMPUTING
COUNTING
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online AccessGet full text

Cover

More Information
Summary:Machine Learning based ranking models are ubiquitous in powering recommendation engines at internet companies. These models typically use a combination of real-valued numerical and categorical features to generate predictions. Feature selection may be a widely encountered problem in this setting, that entails picking the optimal set of features as inputs to these models from a large pool of candidate real-valued and categorical features. A novel feature selection algorithm for categorical features building on stochastic neural networks is provided. It is shown empirically through results, the superiority of this algorithm over existing approaches. Study and proposal of best practices are also provided to practitioners to extract maximum value out of the new feature selection approach.
Bibliography:Application Number: US202218048793