خلاصة:
Stock trend forecasting is a one of the main factors in choosing the best investment,
hence prediction and comparison of different firms’ stock trend is one
method for improving investment process. Stockholders need information for
forecasting firm’s stock trend in order to make decision about firms’ stock trading.
In this study stock trend, forecasting performs by data mining algorithm. It should
mention that this research has two hypotheses. It aimed at being practical and it is
correlation methodology. The research performed in deductive reasoning. Hypotheses
analyzed based on collected data from 180 firms listed in Tehran stock
exchange during 2009-2015. Results indicated that algorithms are able to forecast
negative stock return. However, random forest algorithm is more powerful than
decision tree algorithm. In addition, stock return from last three years and selling
growth are the main variables of negative stock return forecasting.
ملخص الجهاز:
Stock trend forecasting, Random forest algorithm, Decision tree algorithm ABSTRACT Stock trend forecasting is a one of the main factors in choosing the best invest- ment, hence prediction and comparison of different firms’ stock trend is one method for improving investment process.
2 Literature Review Delen et al [9] studied firms’ bankruptcy forecasting in Tehran stock exchange by decision tree and random forest.
Research results indicated that both models (decision tree and random forest) are able to forecast bankruptcy with different accuracy.
[9] evaluated performance of business unit by financial ratio and decision tree by applying four algorithms and studied financial ratios forcasting power for performance assessment indices (stock exchange revenue return and assets’ return).
Deductive reasoning and ex post facto were used as method of the study and decision tree and random forest algorithms were applied for forecasting stock negative return, so that required information and data were collected by library method and using Rah-Avard Novin software and also studying fundamental financial statements of companies listed in Tehran stock exchange during 2009-2015.
Next, decision tree and random forest used for forecasting stock negative return.
Random forest algorithm chooses the best model for stock return forecasting by test and error and by adding and omitting variables in the formula.
As it is indicated in Table 4, random forest algorithm was able to accurately forecast 226 negative return out of 244 negative re- turns of total experiment data.
40%, it is concluded that decision tree has high power of stock return forecasting.