Prediction Models for Startups Success: A Empirical Analysis

Abstract

Small and Medium-Scale Enterprises have been recognized by the government due to their significant role in the country’s economy. The risk of capital investment is high in the enterprises and various factors need to be properly analyzed for the prediction of success of an enterprise. Machine learning techniques can be adopted to predict the success of startups that helps the entrepreneur to make a decision accordingly. In this paper, a details analysis has been carried out on the existing methodologies on startup success prediction to analyze the benefits and limitations. Fewer researches has been carried out in the startup success prediction and achieves the considerable prediction performance. Major limitation has been found among startup success prediction model that use irrelevant features. Some researchers have used social media datasets like Twitter data to increase the performance of the developed method. From existing methods, it has been observed that Random Forest classifiers have been out performed than Logistic Regression method.

Generic entrepreneurship education program design for universities

“…Entrepreneurship education would be useful if the required infrastructure were available. Infrastructure for entrepreneurship education was needed to turn the students into entrepreneurs and help achieve the entrepreneurship education objectives in an organized, effective, and efficient way (Allu et al, 2020). Those were entrepreneurship centres, business incubators, and laboratories to transfer technology, networking, and academicians.…”

Machine learning models for early‐stage investment decision making in startups

“…Over the years, researchers have explored various approaches to predict startup success, employing statistical analyses and machine learning techniques (Allu & Padmanabhuni, 2020; Pasayat et al, 2022). By analyzing historical data and extracting patterns, predictive models have been developed to aid decision making in the dynamic and uncertain world of startups (Brown & Rocha, 2020; Khayrutdinov et al, 2022).…”