Success and Failure Predictions of FinTech Startups
Hristodoulakis, Axel
Promotor(s) : Hübner, Georges
Date of defense : 19-Jun-2020/23-Jun-2020 • Permalink : http://hdl.handle.net/2268.2/8945
Details
Title : | Success and Failure Predictions of FinTech Startups |
Translated title : | [fr] Prédiction du succès et de l'échec de FinTech Startups |
Author : | Hristodoulakis, Axel |
Date of defense : | 19-Jun-2020/23-Jun-2020 |
Advisor(s) : | Hübner, Georges |
Committee's member(s) : | Heuchenne, Cédric
Lamest, Markus Esch, Louis |
Language : | English |
Number of pages : | 119 |
Keywords : | [en] FinTech [en] Startup [en] Failure Prediction [en] Logistic Regression [en] Lasso [en] SMOTE [en] ADASYN |
Discipline(s) : | Business & economic sciences > Finance |
Target public : | Professionals of domain |
Institution(s) : | Université de Liège, Liège, Belgique |
Degree: | Master en ingénieur de gestion, à finalité spécialisée en Financial Engineering |
Faculty: | Master thesis of the HEC-Ecole de gestion de l'Université de Liège |
Abstract
[en] This project-thesis aims to find how to predict the future success or failure of a particular type of firms, that is to say the FinTech startups, based on information available at their establishment. To do so, the FinTech industry was inspected in details. Its evolution and last trends are depicted in the first part of the investigation. In addition, a state of the art of corporate failure prediction summarizing this practice from its premises in the 60s until today is displayed. To carry on this analysis, I decided to conduct a binary logistic regression on a sample of FinTech startups with the objective to separate failing and successful ones. Furthermore, I applied a feature selector, specifically the Least Absolute Shrinkage and Selection Operator (Tibshirani, 1996), on the analysis. Moreover, as the sample used is rather small and imbalanced, I decided to apply an over-sampling technique on it.
File(s)
Document(s)
Description: -
Size: 2.6 MB
Format: Adobe PDF
Annexe(s)
Description: Données
Size: 181.68 kB
Format: Microsoft Excel XML
Description: -
Size: 11.45 kB
Format: Microsoft Excel XML
Cite this master thesis
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.