Man vs. Machine in Predicting Successful Entrepreneurs : Evidence from a Business Plan Competition in Nigeria

Man vs. Machine in Predicting Successful Entrepreneurs : Evidence from a Business Plan Competition in Nigeria

This paper compares the relative performance of man and machine in being able to predict outcomes for entrants in a business plan competition in Nigeria. The first human predictions are business plan scores from judges, and the second are simple ad...

Full description

Bibliographic Details
Main Authors: McKenzie, David, Sansone, Dario
Format: Working Paper
Language:English
Published: World Bank, Washington, DC 2017
Subjects:
ENTREPRENEURSHIP
MACHINE LEARNING
BUSINESS PLANS
ENTERPRISE DEVELOPMENT
Online Access:http://documents.worldbank.org/curated/en/968231513116778571/Man-vs-machine-in-predicting-successful-entrepreneurs-evidence-from-a-business-plan-competition-in-Nigeria
http://hdl.handle.net/10986/29007
id okr-10986-29007
recordtype oai_dc
spelling okr-10986-290072021-06-08T14:42:47Z Man vs. Machine in Predicting Successful Entrepreneurs : Evidence from a Business Plan Competition in Nigeria McKenzie, David Sansone, Dario ENTREPRENEURSHIP MACHINE LEARNING BUSINESS PLANS ENTERPRISE DEVELOPMENT This paper compares the relative performance of man and machine in being able to predict outcomes for entrants in a business plan competition in Nigeria. The first human predictions are business plan scores from judges, and the second are simple ad hoc prediction models used by researchers. The paper compares these (out-of-sample) performances with those of three machine learning approaches. The results show that (i) business plan scores from judges are uncorrelated with business survival, employment, sales, or profits three years later; (ii) a few key characteristics of entrepreneurs such as gender, age, ability, and business sector do have some predictive power for future outcomes; (iii) modern machine learning methods do not offer noticeable improvements; (iv) the overall predictive power of all approaches is very low, highlighting the fundamental difficulty of picking winners; and (v) the models do twice as well as random selection in identifying firms in the top tail of performance. 2017-12-15T18:06:13Z 2017-12-15T18:06:13Z 2017-12 Working Paper http://documents.worldbank.org/curated/en/968231513116778571/Man-vs-machine-in-predicting-successful-entrepreneurs-evidence-from-a-business-plan-competition-in-Nigeria http://hdl.handle.net/10986/29007 English Policy Research Working Paper;No. 8271 CC BY 3.0 IGO http://creativecommons.org/licenses/by/3.0/igo World Bank World Bank, Washington, DC Publications & Research Publications & Research :: Policy Research Working Paper Africa Nigeria
repository_type Digital Repository
institution_category Foreign Institution
institution Digital Repositories
building World Bank Open Knowledge Repository
collection World Bank
language English
topic ENTREPRENEURSHIP
MACHINE LEARNING
BUSINESS PLANS
ENTERPRISE DEVELOPMENT
spellingShingle ENTREPRENEURSHIP
MACHINE LEARNING
BUSINESS PLANS
ENTERPRISE DEVELOPMENT
McKenzie, David
Sansone, Dario
Man vs. Machine in Predicting Successful Entrepreneurs : Evidence from a Business Plan Competition in Nigeria
geographic_facet Africa
Nigeria
relation Policy Research Working Paper;No. 8271
description This paper compares the relative performance of man and machine in being able to predict outcomes for entrants in a business plan competition in Nigeria. The first human predictions are business plan scores from judges, and the second are simple ad hoc prediction models used by researchers. The paper compares these (out-of-sample) performances with those of three machine learning approaches. The results show that (i) business plan scores from judges are uncorrelated with business survival, employment, sales, or profits three years later; (ii) a few key characteristics of entrepreneurs such as gender, age, ability, and business sector do have some predictive power for future outcomes; (iii) modern machine learning methods do not offer noticeable improvements; (iv) the overall predictive power of all approaches is very low, highlighting the fundamental difficulty of picking winners; and (v) the models do twice as well as random selection in identifying firms in the top tail of performance.
format Working Paper
author McKenzie, David
Sansone, Dario
author_facet McKenzie, David
Sansone, Dario
author_sort McKenzie, David
title Man vs. Machine in Predicting Successful Entrepreneurs : Evidence from a Business Plan Competition in Nigeria
title_short Man vs. Machine in Predicting Successful Entrepreneurs : Evidence from a Business Plan Competition in Nigeria
title_full Man vs. Machine in Predicting Successful Entrepreneurs : Evidence from a Business Plan Competition in Nigeria
title_fullStr Man vs. Machine in Predicting Successful Entrepreneurs : Evidence from a Business Plan Competition in Nigeria
title_full_unstemmed Man vs. Machine in Predicting Successful Entrepreneurs : Evidence from a Business Plan Competition in Nigeria
title_sort man vs. machine in predicting successful entrepreneurs : evidence from a business plan competition in nigeria
publisher World Bank, Washington, DC
publishDate 2017
url http://documents.worldbank.org/curated/en/968231513116778571/Man-vs-machine-in-predicting-successful-entrepreneurs-evidence-from-a-business-plan-competition-in-Nigeria
http://hdl.handle.net/10986/29007
_version_ 1764468254065033216

Similar Items