Open AccessMachine Learning based Pricing Methodology for the Logistic Domain: a Preliminary Approach
Author(s) -
Antonio L. Amadeu,
Fernando Vinturin,
Guilherme Augusto Zimeo Morais,
Maickel Hubner,
Eduardo M. Pereira,
Marcelo Santos
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/semish.2021.15819
Subject(s) - silhouette , computer science , domain (mathematical analysis) , feature engineering , cluster analysis , work (physics) , market segmentation , process (computing) , logistic regression , data science , artificial intelligence , machine learning , marketing , business , deep learning , engineering , mathematics , mechanical engineering , mathematical analysis , operating system
In this work, we introduce a new methodology to discover logistic regions for pricing. We use value-based characteristics from different sources, such as demographic, socioeconomic, risk, transportation, among others, to find homogeneous and valuable pricing regions. The problem was formulated as a traditional cluster solution, where well-know metrics, such as BIC and silhouette score, were used for technical validation, and business premises and constraints, operational and sales, where used to enrich feature engineering and refine cluster formation. The results presented here are from a preliminary work that was validated through several sessions with stakeholders of interest, but it is still missing the market validation. Indeed, this work will be deployed soon and a more detailed validation process, including client adherence, will be performed and monitored until the end of this year.