This research aims to predict future sequences of inflation and investor sentiment index using artificial intelligence in two countries, Iran and Iraq. The present research is applied in terms of purpose and descriptive-analytical in terms of nature and method, and has been conducted with a mixed approach (artificial intelligence and econometrics). The statistical population includes monthly data related to inflation and investor sentiment index in Iran and Iraq, and the statistical sample includes all available observations in the 10-year period ending in October 2025. The data has been collected through documentary methods and from official statistical sources and reliable databases. In the first stage, LSTM recurrent neural network was used to predict future sequences of both variables; in such a way that 80% of the data was considered for training and 20% for testing, and the predictions were evaluated in the form of seven future sequences. The results of this section showed that the model performed more consistently and reliably in predicting the Iranian investor sentiment index, while in Iraq, the error gradually increased with the increase in the forecast horizon. The results of the error correction model also showed that in both countries, a long-term equilibrium relationship exists between the variables and the system returns to the equilibrium path at an appropriate speed.