Articles Entrepreneurship

Start-up Companies Predictive Models Analysis

Abstract: A quantitative research is performed to derive a model for predicting the success of Bulgarian start-up companies. The preceding research stages included an overview and analysis of older success prediction models, a new abstract success prediction model, a venture creation process model and a qualitative research. The abstract success prediction model is extended with measurable variables which are included in a survey. The survey is currently in progress with 105 responses by owners and managers of Bulgarian companies. The current dataset was analyzed using the IBM SPSS Modeler software which automatically tests different models and suggests the best performing ones. The best derived model is a decision tree model that predicts the success of the start-up companies from the dataset with 91,86% probability using 11 variables.

Authors: Yankov, B., Haralampiev, K., Ruskov P.