Could Machine Learning Predict the Conversion in Motor Business?

Lorenzo Invernizzi () and Vittorio Magatti ()
Additional contact information
Lorenzo Invernizzi: Zurich Insurance Company Ltd
Vittorio Magatti: Sapienza Universita’ di Roma

A chapter in Mathematical and Statistical Methods for Actuarial Sciences and Finance, 2018, pp 431-435 from Springer

Abstract: Abstract The aim of the paper is to estimate the Conversion Rate by means of three Machine Learning (ML) algorithms: Classification and Regression Tree (CART), Random Forest (RF) and Gradient Boosted Tree (BOOST). The Generalized Linear Model (GLM), benchmark model in the framework, is used as frame of reference. The RF model has the highest Recall, while the BOOST is the most precise model. The RF is able to outperform the GLM benchmark model in terms of Log Loss error, Precision, Recall and F Score. Variable Importance and Strength index, computed from the ML models and the GLM respectively, describe how the different algorithms are coherent on choosing the most relevant features.

Keywords: Machine learning; Conversion rate; Generalized linear model; CART; Random forest; Gradient boosting; Motor insurance (search for similar items in EconPapers)
Date: 2018
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-319-89824-7_77

Ordering information: This item can be ordered from
http://www.springer.com/9783319898247

DOI: 10.1007/978-3-319-89824-7_77

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().