The Pattern of Return Changes based on Profit Forecast Changes with a Behavioral Finance Approach in the Framework of the Role of Anchor bias
The purpose of this article is to compare conditional heterogeneous variance models and artificial neural network in explaining the changes in returns based on the changes in profit forecast with behavioral finance approach. Anchor bias refers to judgment or decision making based on the initial info...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Alzahra University
2025-06-01
|
| Series: | راهبرد مدیریت مالی |
| Subjects: | |
| Online Access: | https://jfm.alzahra.ac.ir/article_8632_8403ce3d7628884f2c35a01d348abd8e.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The purpose of this article is to compare conditional heterogeneous variance models and artificial neural network in explaining the changes in returns based on the changes in profit forecast with behavioral finance approach. Anchor bias refers to judgment or decision making based on the initial information received. The initial and previous data that exists on a subject affects the investor on a subject or causes a biased decision to be made. For this purpose, the information of the time period 2011-2023 was used with seasonal frequency. In this regard, the return was modeled based on changes in profit forecast using the autocorrelated moving average (ARMA) model, and the fluctuations of this return were modeled using the generalized autoregressive conditional heteroscedastic (GARCH). Next, profit forecasting was done using the neural network method and the accuracy of this model was compared with time series methods. The results obtained in this study indicated that there is a positive and significant relationship between anchorage exploitation and profit forecasting error. In addition to this, the obtained results have shown that the accuracy of the neural network method in predicting profit changes is higher than the ARMA and GARCH models. |
|---|---|
| ISSN: | 2345-3214 2538-1962 |