This research evaluates the efficacy of survival models in forecasting startup failures and investigates their economic implications. Several machine learning survival models, including Kernel SVM, DeepSurv, Survival Random Forest, and MTLR, are assessed using the concordance index (C-index) as a measure of prediction accuracy. The findings reveal that more sophisticated models, such as Multi-Task Logical Regression (MTLR) and Random Forest, outperform the standard Cox and Kaplan Meier (K-M) models in terms of predicted accuracy.

Because of the complexity of indirect financial intermediary services (FISIM) accounting, the traditional price index deflation method can no longer meet its accounting needs. The manual of price and volume measurement suggests that the stock deflation method and output index method should be used to calculate the volume of FISIM. Comparing the two accounting frameworks, it can be found that the key to the implementation of the stock deflation method is to set a scientific and reasonable deflation index from two aspects of service price and the service quantity, while the key of the output index method is the selection of the output index and the determination of weight. This paper compares the application cases of stock deflation method and output index method in practice, summarizes the similarities, differences, advantages and disadvantages of each case in index construction, index selection and weight determination, and further provides a reference for China FISIM volume accounting.