محاسبه احتمال سقوط سهام با استفاده از شبکه های عصبی پیچیده و بررسی رابطه بین احتمال سقوط سهام و بازده انتظاری سهام در بازار سرمايه)1386-ايران) 1400

One of the most destructive fluctuations in the stock market is the crash in stock prices. The accurate calculation of the probability of the stock price crash can greatly help investors choose the right investment portfolio. In this article, the one-dimensional convolutional neural network technique is used to calculate the probability of the stock price crash, and the three-factor Fama and French model and Capital asset pricing model are used to calculate stock returns. The sample used in this paper includes 80 import- and export-oriented exchange companies in the period 2008-2021 According to the obtained results, convolutional neural networks predict the probability of the stock crash with high accuracy, and there is an inverse relationship between the probability of the stock price crash and its expected return, which means that by calculating the probability of a stock price crash, it is possible to predict the future demand for it and the direction of its future price. Calculating the probability of stock price crashes, using convolutional neural networks is a new method for calculating the risk of stock price crash and can help us measure portfolio risk. [ABSTRACT FROM AUTHOR]