• Login
    View Item 
    •   MMUST Institutional Repository
    • University Journals/ Articles
    • Gold Collection
    • View Item
    •   MMUST Institutional Repository
    • University Journals/ Articles
    • Gold Collection
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Random forest model for predicting business success for micro, small and medium enterprises in Kakamega County, Kenya

    Thumbnail
    View/Open
    Random+forest+model+for+predicting+business+success+for+micro,+small+and+medium+enterprises+in+Kakamega+County,+Kenya+-+Khagayi+et+al.+-+AJERNET.pdf (211.6Kb)
    Date
    2025-07-21
    Author
    Khagayi, Sandra
    Odoyo, Collins
    Rambim, Dorothy
    Metadata
    Show full item record
    Abstract
    The Micro, Small, and Medium Enterprises (MSMEs) are an important part of the economy of Kenya, yet they have a high rate of uncertainty and failure because of complicated, poorly comprehended reasons. This paper has come up with a machine learning model based on the Random Forest algorithm to forecast the success of MSMEs in Kakamega County, Kenya, based on historical data provided by the county government. The study was guided by resource-based view theory which posits that a business’s success and sustainability hinge on its ability to acquire, control and utilize valuable internal resources. The traditional approaches that limit themselves to linear financial indicators have been inadequate in describing the multidimensional risks experienced by MSMEs. The study adopted simulation research design to develop a predictive model based on the Random Forest algorithm to predict the success of MSMEs. Random Forest model has shown outstanding predictive accuracy with a precision of 99.72 percent in predicting the success of businesses. The major predictors were found to be the availability of financial access, business characteristics and government support factors. A binary logistic regression model was also used to confirm the results and explained 99.64 percent of the variance in business outcomes. The findings provide a solid basis of evidence-based policy-making and interventions in support. The research is an addition to the existing evidence on the applicability of machine learning in enterprise sustainability and offers a scalable solution to enhancing the resilience of MSMEs in comparable settings. The study successfully developed highly accurate machine learning model for predicting MSME success. It was able to identify critical factors for MSME success, financial access and government support.The study recommends that policy makers and stake-holders should utilize data-driven insights for targeted interventions to enhance MSME resilience and growth. To foster growth and development, MSMEs are advised to focus on improving financial management and leveraging government support programs.
    URI
    http://ir-library.mmust.ac.ke:8080/xmlui/handle/123456789/3225
    Collections
    • Gold Collection [996]

    MMUST Library copyright © 2011-2022  MMUST Open Access Policy
    Contact Us | Send Feedback
     

     

    Browse

    All of Institutional RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    MMUST Library copyright © 2011-2022  MMUST Open Access Policy
    Contact Us | Send Feedback