Recommending Data Preprocessing Pipelines for Machine Learning Applications in Production

Beschreibung

High data quality is the key for performant machine learning (ML) models in produc-tion. In practice, data quality is preprocessed using several DPP methods that are configured into DPP pipelines. The choice of the DPP pipelines poses a major chal-lenge. To guide data scientists, a meta learning-based decision support system (DSS) have been developed, called Meta-DPP, which assists in the selection of suitable DPP pipelines but do not cover production-specific requirements.

Autor*in

Maik Frye

Themen in »Recommending Data Preprocessing Pipelines for Machine Learning Applications in Production«

Maschinendatenanalyse Quality Intlligence Produktionsqualität

Stimmen zu »Recommending Data Preprocessing Pipelines for Machine Learning Applications in Production«

Details

Link teilen