Machine learning based fraud detection and credit risk assessment for SME credits

Development of novel fraud detection and credit risk assessment methods for SME credits. The goal is to develop machine learning based algorithms and models that combine various types of data in order to obtain improved predictive accuracy.

Brief information

School:

Business

Status:

Completed

Period:

01.01.2017 - 01.03.2019

Overview

Development of novel fraud detection and credit risk assessment methods for SME credits. The goal is to develop machine learning based algorithms and models that combine various types of data in order to obtain improved predictive accuracy.

Facts

Type of project

Forschung

Internal organisations involved
  • Institute of Financial Services Zug IFZ
  • CC Financial Services
  • CC Corporate Finance
Funding
  • KTI-HSLU als Hauptgesuchsteller/in
  • Private / Stiftungen

Persons involved: internal

Project manager
Member of project team

Publications

    • Sigrist, Fabio (2022). Gaussian Process Boosting. Journal of Machine Learning Research (JMLR), 2022(23), 1-46.

    • Sigrist, Fabio (2021). KTBoost: Combined kernel and tree boosting. Neural Processing Letters, 2021(2), 1147-1160.

    • Sigrist, Fabio (2021). Gradient and newton boosting for classification and regression. Expert Systems With Applications, 2021(167), 114080.

    • Hirnschall, Christoph & Sigrist, Fabio (2019). Grabit: Gradient tree-boosted Tobit models for default prediction. Journal of Banking & Finance, 2019(102), 177-192.