Predicting the Success of a Startup in Information Technology Through Machine Learning

Predicting the success of a startup in information technology (SIT) is very complex problem due to diverse factors and uncertainty that affects it. The focus automatic learning (ML) promising because it presents good results for prediction issues; however, diversity parameters, factors, data require consideration improve results. In this study, systematic method proposed build predictive model SIT success, based on factors. consists four processes, hybrid model, an inventory 79 was applied database 265 SITs from Australia with seven ML algorithms three models Voting strategy GreedyStepwise algorithm reduce On average, precision increments 11.69%, specificity 3.25%, accuracy 21.75%; has 82% 88%.