Regional investment risk evaluation based on compound risk correlation coefficient and migration learning approach

Abstract

The high profit of regional investment is often accompanied by high risks, and the prior assessment of investment risks is conducive to avoid investment risks. However, the traditional evaluation methods usually only focus on individual risk factors, and it is difficult to evaluate and manage risks on the whole. Therefore, the study introduces deep learning algorithm, first build regional investment risk evaluation index system, then according to the characteristics of risk evaluation, design based on deep learning regional investment risk evaluation model, the final use parameter based migration learning algorithm and composite correlation coefficient to improve the evaluation model, solve the problem of insufficient training samples. The test results showed that the randomly selected 50 test samples with two different risk assessment models were 0.80 and 0.86, the deep learning algorithm tested 0.84, and the transfer learning improved model tested was 0.92, with the highest accuracy. This shows that the deep learning regional investment risk evaluation model improved by transfer learning effectively solves the problem of insufficient training data and improves the accuracy of prediction evaluation. In the field of venture capital, the model can help investors to evaluate and predict investment risks more accurately and improve the effect of investment decisions.