Research on quality evaluation of innovation and entrepreneurship education for college students based on random forest algorithm and logistic regression model.

The quality evaluation of innovation and entrepreneurship (I&E) in the education sector is achieving worldwide attention as empowering nations with high quality talents is quintessential for economic progress. China, a pioneer in the world market in almost all sectors have transformed its educational policies and incorporated entrepreneurial skills as a part of their education models to further catalyst the country's economic progress. This research focuses on building a novel hybrid Machine Learning (ML) model by integrating two powerful algorithms namely Random Forest (RF) and Logistic Regression (LR) to assess the intensity of the I&E in education from the data acquired from 25 leading Higher Educational Institution's (HEI) in different provinces. The major contributions to the work are, (1) construction of quality index for each topic of interest using individual RF, (2) ranking the indicators based on the quality index to assess the strength and weaknesses, (3) and finally use the LR algorithm study the quality of each indicator. The efficacy of the proposed hybrid model is validated using the benchmark classification metrics to assess its learning and prediction performance in evaluating the quality of I&E education. The result of the research portrays that the universities have now started to integrate entrepreneurship skills as a part of the curriculum, which is evident from the better ranking of the topic curriculum development which is followed by the enrichment of skills. This comprehensive research will help the institutions to identify the potential areas of growth to boost the economic development and improve the skill set necessary for I&E education among college students.