Header

UZH-Logo

Maintenance Infos

The value of publicly available, textual and non-textual information for startup performance prediction


Kaiser, Ulrich; Kuhn, Johan M (2020). The value of publicly available, textual and non-textual information for startup performance prediction. Journal of Business Venturing Insights, 14:e00179.

Abstract

We use administrative textual and non-textual data retrieved from publicly available archives to predict the performance of Danish startups at the time of foundation. The performance outcomes we consider are survival, high employment growth, a return on assets of above 20 percent, new patent applications and participation in an innovation subsidy program. We consider a base specification that includes variables for legal form, region, ownership and industry in all specifications and add variable sets representing firm names, business purpose statements (BPSs) as well as founder and startup characteristics. To forecast the two innovation-related performance outcomes well, we only need to include a set of variables derived from the BPS texts on top of the base variables while an accurate prediction of startup survival requires the combination of the firm names and the BPS variables along with founder characteristics. An accurate forecast of high employment growth needs the combination of the BPS variables and the founder characteristics. All information our forecasts require is likely to be easily obtainable since the underlying information is mandatory to report upon business registration in many countries. The substantial accuracy of our predictions for survival, employment growth, new patents and participation in innovation subsidy programs indicates ample scope for algorithmic scoring models as an additional pillar of funding and innovation support decisions.

Abstract

We use administrative textual and non-textual data retrieved from publicly available archives to predict the performance of Danish startups at the time of foundation. The performance outcomes we consider are survival, high employment growth, a return on assets of above 20 percent, new patent applications and participation in an innovation subsidy program. We consider a base specification that includes variables for legal form, region, ownership and industry in all specifications and add variable sets representing firm names, business purpose statements (BPSs) as well as founder and startup characteristics. To forecast the two innovation-related performance outcomes well, we only need to include a set of variables derived from the BPS texts on top of the base variables while an accurate prediction of startup survival requires the combination of the firm names and the BPS variables along with founder characteristics. An accurate forecast of high employment growth needs the combination of the BPS variables and the founder characteristics. All information our forecasts require is likely to be easily obtainable since the underlying information is mandatory to report upon business registration in many countries. The substantial accuracy of our predictions for survival, employment growth, new patents and participation in innovation subsidy programs indicates ample scope for algorithmic scoring models as an additional pillar of funding and innovation support decisions.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

68 downloads since deposited on 14 Jan 2021
43 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Business Administration
Dewey Decimal Classification:330 Economics
Scopus Subject Areas:Social Sciences & Humanities > Business and International Management
Social Sciences & Humanities > Management of Technology and Innovation
Scope:Discipline-based scholarship (basic research)
Language:English
Date:1 November 2020
Deposited On:14 Jan 2021 13:13
Last Modified:11 Jun 2024 03:30
Publisher:Elsevier
ISSN:2352-6734
OA Status:Hybrid
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1016/j.jbvi.2020.e00179
Other Identification Number:merlin-id:20205
  • Content: Published Version
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)