Ex Ante Predictability of Rapid Growth: A Design Science Approach

Ari Hyytinen; Petri Rouvinen; Mika Pajarinen; Joosua Virtanen

doi:10.1177/10422587221128268

Ex Ante Predictability of Rapid Growth: A Design Science Approach

Ari Hyytinen^*
, Petri Rouvinen
, Mika Pajarinen
, Joosua Virtanen

^*Corresponding author for this work

Research output: Contribution to journal › Article › Scientific › peer-review

9 Citations (Scopus)

Abstract

We examine how machine learning (ML) predictions of high-growth enterprises (HGEs) help a budget-constrained venture capitalist source investments for a fixed size portfolio. Applying a design science approach, we predict HGEs 3 years ahead and focus on decision (not statistical) errors, using an accuracy measure relevant to the decision-making context. We find that when the ML procedure adheres to the budget constraint and maximizes the accuracy measure, nearly 40% of the HGE predictions are correct. Moreover, ML performs particularly well where it matters in practice—in the upper tail of the distribution of the predicted HGE probabilities.

Original language	English
Peer-reviewed scientific journal	Entrepreneurship Theory and Practice
ISSN	1042-2587
DOIs	https://doi.org/10.1177/10422587221128268
Publication status	Published - 06.11.2022
MoE publication type	A1 Journal article - refereed

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 12 Responsible Consumption and Production

Keywords

511 Economics
high-growth enterprises
relevance
prediction
design research
machine learning

Access to Document

10.1177/10422587221128268Licence: CC BY

10422587221128268Final published version, 575 KBLicence: CC BY

OpenUrl availability

Full text

Cite this

@article{2972f03c89fe4dcb95de100dfea5e7ff,

title = "Ex Ante Predictability of Rapid Growth: A Design Science Approach",

abstract = "We examine how machine learning (ML) predictions of high-growth enterprises (HGEs) help a budget-constrained venture capitalist source investments for a fixed size portfolio. Applying a design science approach, we predict HGEs 3 years ahead and focus on decision (not statistical) errors, using an accuracy measure relevant to the decision-making context. We find that when the ML procedure adheres to the budget constraint and maximizes the accuracy measure, nearly 40\% of the HGE predictions are correct. Moreover, ML performs particularly well where it matters in practice—in the upper tail of the distribution of the predicted HGE probabilities.",

keywords = "511 Economics, high-growth enterprises, relevance, prediction, design research, machine learning",

author = "Ari Hyytinen and Petri Rouvinen and Mika Pajarinen and Joosua Virtanen",

year = "2022",

month = nov,

day = "6",

doi = "10.1177/10422587221128268",

language = "English",

journal = "Entrepreneurship Theory and Practice",

issn = "1042-2587",

publisher = "Universit{\'e} du Qu{\'e}bec {\`a} Montr{\'e}al",

}

TY - JOUR

T1 - Ex Ante Predictability of Rapid Growth: A Design Science Approach

AU - Hyytinen, Ari

AU - Rouvinen, Petri

AU - Pajarinen, Mika

AU - Virtanen, Joosua

PY - 2022/11/6

Y1 - 2022/11/6

N2 - We examine how machine learning (ML) predictions of high-growth enterprises (HGEs) help a budget-constrained venture capitalist source investments for a fixed size portfolio. Applying a design science approach, we predict HGEs 3 years ahead and focus on decision (not statistical) errors, using an accuracy measure relevant to the decision-making context. We find that when the ML procedure adheres to the budget constraint and maximizes the accuracy measure, nearly 40% of the HGE predictions are correct. Moreover, ML performs particularly well where it matters in practice—in the upper tail of the distribution of the predicted HGE probabilities.

AB - We examine how machine learning (ML) predictions of high-growth enterprises (HGEs) help a budget-constrained venture capitalist source investments for a fixed size portfolio. Applying a design science approach, we predict HGEs 3 years ahead and focus on decision (not statistical) errors, using an accuracy measure relevant to the decision-making context. We find that when the ML procedure adheres to the budget constraint and maximizes the accuracy measure, nearly 40% of the HGE predictions are correct. Moreover, ML performs particularly well where it matters in practice—in the upper tail of the distribution of the predicted HGE probabilities.

KW - 511 Economics

KW - high-growth enterprises

KW - relevance

KW - prediction

KW - design research

KW - machine learning

UR - https://www.scopus.com/pages/publications/85141622981

U2 - 10.1177/10422587221128268

DO - 10.1177/10422587221128268

M3 - Article

SN - 1042-2587

JO - Entrepreneurship Theory and Practice

JF - Entrepreneurship Theory and Practice

ER -

Ex Ante Predictability of Rapid Growth: A Design Science Approach

Abstract

UN SDGs

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint