Anzeige
Erschienen in:
2019 | OriginalPaper | Buchkapitel
7. Software Implementations
verfasst von : René Michel, Igor Schnakenburg, Tobias von Martens
Erschienen in: Targeting Uplift
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
This chapter looks at different software implementations in order to mention which net scoring methods have been implemented in software packages and how those packages have to be handled. Different implementations, such as SAS, R, Pitney Bowes, and others, are presented and comments on their level of proficiency but also on their shortcomings are given. Remarks will be made with respect to the usability and the comfort offered by the different packages with regard to uplift model development, scoring, evaluation, deployment, and visualizations. For each presented software, some general comments on the provider and the package will be made. We detail the way that model preparation is supported, model building and scoring are handled, evaluation is implemented, and a roll-out may be automated. In the end, a comparative study will be presented where a net scoring model is built with each software on an identical dataset.