A Machine Learning Tool to Predict Early-Stage Start-Up Success in Africa - Master of Science in Computing and Information Systems

Aug 4, 2026

Upload by Asher

Most start-ups do not reach their first year in operation, and only a minority survive beyond five years, creating a persistent challenge for entrepreneurs, investors, and other stakeholders. This study evaluates the determinants of early-stage start-up success in Africa and builds a web-based prediction prototype using machine learning. Secondary data from CrunchBase supports model development, with 80% for training and 20% for testing/validation. Artificial Neural Networks power the model and achieve 86.81% accuracy. The prototype is implemented with Flask and Python ML frameworks (Keras, scikit-learn) and validated through user usability feedback.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages93

Reading Time3 h 54 min

AccessFree to download

Chapter 1: Introduction

1.1 Background of the Study

1.2 Problem Statement

1.3 Research Objectives

Electronic Thesesand Dissertations 2023 A Machine learning tool to predict earlystage start-up success in Africa. Gichohi, Brian Waihiga School of Computing and Engineering Sciences Strathmore University RecommendedCitation Gichohi, B. W. (2023) . A Machine learning tool to predict early-stage start-up success in Africa [Strathmore University] . [http://hdl.handle.net/11071/15384](http://hdl.handle.net/11071/15384) Follow this andadditional works at: [http://hdl.handle.net/11071/15384](http://hdl.handle.net/11071/15384) A Machine Learning Tool to Predict Early-Stage Start-Up Success in Africa Brian Waihiga Gichohi 138134 Master of Science in Computing and Information Systems 2023 A Machine Learning Tool to Predict Early-Stage Start-Up Success in Africa Brian Waihiga Gichohi 138134 Submitted in partial fulfillment of the requirements for the Degree of Master of Science in Computing and Information Systems at Strathmore University School of Computing and Engineering Sciences Strathmore University Nairobi, Kenya June 2023 This thesis is available for Library use on the understanding that it is copyright material and that no quotation from the thesis may be published without proper acknowledgement. Declaration I declare that this work has not been previously submitted and approved for the award of a degree by this or any other University. To the best of my knowledge and belief, the thesis contains no material previously published or written by another person except where due reference is made in the thesis itself. © No part of this thesis may be reproduced without the permission of the author and Strathmore University Student’s Name: Brian Waihiga Gichohi Sign: Date: 22nd May 2023 Approval This dissertation was done by Brian Waihiga Gichohi and was reviewed and approved by the following: Dr. Bernard Shibwabo Senior Lecturer, School of Computing and Engineering Sciences, Strathmore University Dr. Julius Butime, Dean, School of Computing & Engineering Sciences, Strathmore University Dr. Bernard Shibwabo, Director of Graduate Studies, Strathmore University Abstract Most start-ups do not celebrate their first year in operation, and a few survive to see their fifth year of operation. This has been a challenge for all the stakeholders involved. Therefore, an effective tool for predicting the possibility of a start-up surviving its infancy stages and eventually growing into a profitable venture could be a breakthrough for entrepreneurs, innovators, and investors. This study assessed the factors that make earlystage start-ups successful, specifically in Africa and developed a web-based prototype that uses machine learning algorithms to predict the success of proposed start-ups. The study adopted both descriptive research design and applied research. Data was collected using a secondary data source called CrunchBase, a global investor platform. This data formed the basis for the development of the prediction tool. The tool was designed to predict the successor failure of start-ups based on the collected data. To ensure the accuracy and reliability of the prediction model, 80% of the collected data was used for training the model, while the remaining 20% was utilized for testing and validation purposes. The model development employed Artificial Neural Networks (ANNs) algorithm, known for its capability to analyze complex patterns and relationships in data. The developed model achieved an impressive accuracy of 86.81%, indicating its effectiveness in predicting the success of start-ups. The tool was implemented using Flask, a Python web framework, along with other Python machine learning frameworks such as Keras and Sci-kit Learn. This allowed for the development of a user-friendly and interactive web-based prototype. A number of users were provided access to the tool for usability testing, and their feedback indicated that the tool was intuitive, easy to use, a

FAQs

What problem does the thesis address?

It addresses the low survival rate of early-stage start-ups and the need for an effective tool to predict whether a start-up can survive infancy and grow profitably.

How is the prediction tool developed and validated?

The study uses secondary data from CrunchBase, trains the model with 80% of the data, and validates/testing it with the remaining 20% to ensure reliability.

Which algorithm and technologies are used in the model and prototype?

Artificial Neural Networks (ANNs) are used for prediction. The web-based prototype is implemented with Flask and supporting Python machine learning frameworks such as Keras and scikit-learn.

Aug 4, 2026

Upload by Asher