Abstract
30May 2016 STATISTICAL AND MACHINE TECHNIQUES FOR ASSESSING THE STATUS OF STARTUPS T. Leo Alexander and Marion Nikita Joseph. Associate Professor, Department of Statistics, Loyola College, Chennai – 600 034. Research Scholar, Department of Statistics, Loyola College, Chennai – 600 034.
Highlights
A startup is a young company that is beginning to develop and grow(8), is in the first stages of operation, and is usually financed by an individual or small group of individuals and which could be an entrepreneurial venture or a new business, a partnership or temporary business organization designed to search for a repeatable and scalable business model
Area Under the Curve:The Area under the ROC curve (AUC) obtained for this model is about 0.885 for the train data and 0.901 for test data which is much higher than the Logistic regression model and Classification and Regression Trees (CART) model but is slightly lesser than Random Forest
Having discussed the results from various modeling techniques applied in the study we see that data mining techniques tend to improve the predictive accuracy and gives us interesting insights concerning the success or failure of the startups
Summary
A startup is a young company that is beginning to develop and grow(8), is in the first stages of operation, and is usually financed by an individual or small group of individuals and which could be an entrepreneurial venture or a new business, a partnership or temporary business organization designed to search for a repeatable and scalable business model. We are in the midst of an entrepreneurial revolution that is spreading to nearly every nook and corner on the planet. Even countries plagued with political strife or in the midst of a deep recession are seeing a surge in start-up activity(9). There are a few Challenges for Startups, which are Culture, Awareness, Social Issues, Technology, Financial issues, Sustainability Issues and Regulatory Issues. We will be discussing a quick look into the main objectives of the study and the data sources, methods adopted and Statistical Analysis
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call