Founder Success in Norwegian Startups - A Machine Learning Approach - A study on the use of machine learning and personality traits to predict startup performance from a pre-seed perspective

Aug 4, 2026

This master thesis investigates founder characteristics in Norway’s startup ecosystem and evaluates whether machine learning can support venture capital decisions about founder success at the earliest, pre-seed stage when information is scarce. The authors assemble a dataset of 1,918 tech-driven scalable startups and 2,700 unique founders, including AI-estimated personality traits. Four supervised models classify founders into low- and high-success categories, with XGBoost and Random Forest achieving over 62% accuracy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages112

Reading Time4 h 42 min

AccessFree to download

Abstract

Acknowledgements

1 Introduction

2 Literature Review

2.1 Personality Framework: The Five-Factor Model

2.2 Historical Research on Characteristics of Successful Founders

2.3 Bridging the Gap: The Unique Contributions of This Thesis

3 Data Collection and Construction of Dataset

3.1 Data Collection

3.2 Cleaning and Merging of Data Sources

3.3 Structure of Complete Dataset

4 Defining Startup Success

4.1 Background Research

4.2 Defining a Score for Startup Success

4.3 Classification of Score

Norwegian School of Economics Bergen, Spring, 2023 Founder Success in Norwegian Startups: A Machine Learning Approach A study on the use of machine learning and personality traits to predict startup performance from a pre-seed perspective Alexander Hogstad Wik & Håkon Otterlei Supervisor: Sondre Nedreås Hølleland Master thesis, Economics and Business Administration Major: Business Analytics NORWEGIAN SCHOOL OF ECONOMICS This thesis was written as a part of the Master of Science in Economics and Business Administration at NHH. Please note that neither the institution nor the examiners are responsible − through the approval of this thesis − for the theories and methods used, or results and conclusions drawn in this work. Abstract This thesis aims to investigate founder characteristics in the Norwegian startup ecosystem and if machine learning can help venture capital firm identity successful founders at a startup’s earliest stages, when information is greatly limited. The authors collected and refined data from multiple sources, resulting in a unique dataset of 1918 tech-driven, scalable startups and 2700 unique founders. Especially outstanding in the dataset is the inclusion of personality traits estimated though the use of artificial intelligence. Four supervised machine learning models were employed to classify the founders into two created success categories, low success, and high success. The two tree-based methods, Extreme Gradient Boosting and Random Forest performed best considering the evaluation metrics, resulting in a classification accuracy of over 62%, while Logistic Regression and K-Nearest Neighbours did not follow far behind. The thesis finds significant evidence that the Number of Founders ofa company and the personality trait Conscientiousness are strong predictors of success in the Norwegian startup landscape. Both of our findings showcase a positive correlation with startup performance, meaning entrepreneurs who inherits high Conscientiousness and are part of founding teams are more likely to succeed as entrepreneurs in Norway. The research has two use cases. One, to narrow the research gap on founders in Norwegian startups, and two, motivate venture capital firms in Norway to adapt and implement machine learning models to help with decision-making, despite the challenges of limited data. The authors encourage others to continue research on this area, such as investigating the validity of personality traits obtained through artificial intelligence and broadening and expanding the research to other companies in Norway and other Scandinavian countries. The thesis recognizes the potential ethical considerations that arise when collecting public data on private individuals. The weaknesses of this research are also discussed, which include the chosen data structure and biases in the data. Acknowledgements This thesis is the concluding achievement of our master's degree in Business and Administration, undertaken with a major in Business Analytics, at the Norwegian School of Economics. We wish to express our heartfelt gratitude to our supervisor, Sondre Nedreås Hølleland, for always being available on short notice and his invaluable insights throughout the semester. We also acknowledge the generosity of the Norwegian School of Economics in providing sponsorship for our access to Humantic AI and Forvalt. The invaluable data and resources derived from these platforms significantly enriched our research, contributing substantially to the depth and quality of this thesis. Our appreciation extends to Kjetil Holmefjord, whose enlightening interviews shed invaluable light on the dynamics ofthe venture capital industry in Norway. Lastly, we wish to extend our sincere thanks to our friends and family. Their constant support and encouragement through our study at the Norwegian School of Economics, and in the process of crafting this thesis, were a true source of strength and motivation.

FAQs

What is the main goal of the thesis?

To study whether founder characteristics in Norwegian startups, combined with machine learning, can help predict startup performance at the pre-seed stage for venture capital decision-making.

How was the dataset constructed and what makes it distinctive?

The authors collected and refined data from multiple sources, building a dataset of 1,918 startups and 2,700 founders, with personality traits estimated using AI.

Which machine learning models performed best and what factors were key predictors?

Extreme Gradient Boosting and Random Forest performed best, and the thesis finds strong evidence that the number of founders and the personality trait Conscientiousness are strong predictors of success.

Aug 4, 2026

Upload by Olivia Brown