Accuracy comparison for Stock Price Prediction using Novel Random Forest Algorithm over of Convolutional Neural Network Algorithm

Through the process of contrasting and comparing the two algorithms, which are the Novel Random Forest method and the Convolutional Neural Network (CNN) algorithm, the purpose of this research is to improve the accuracy of stock price predictions. In this study, the purpose is to examine the similarities and differences between the two approaches. The construction of parallels and contrasts between the two approaches will serve as the mechanism that will be utilized in order to attain this purpose. Both the Convolutional Neural Network Algorithm and the Novel Random Forest Algorithm are utilized in the course of their respective applications within the scope of this research project. It is generally agreed that the two groups of algorithms that are being addressed in this article are two distinct sets of algorithms at the same time. The inquiry that is now being carried out makes use of both of these algorithms in order to carry out the investigation. The parameters for alpha (0.05) and beta (0.2) are utilized during the process of establishing the size of the sample since they are used in the process. In addition to the fact that these qualities are taken into consideration throughout the process of selecting the sample size for each group, the sample size for each group includes 10 individuals. The program known as SPSS is utilized in order to carry out the statistical investigations, and the G-power value is set to be 80% while the software is being utilized. This is done in order to ensure that the investigations are carried out accurately. The investigators are doing these investigations with the intention of identifying the level of relevance that the dataset features in order to better understand its contents. For the purpose of achieving the objective of determining the results that are associated with each method, a wide variety of different sample sizes are utilized for each program. As demonstrated by the data, the Novel Random Forest Algorithm is superior to the Convolutional Neural Network Algorithm in terms of its capacity to anticipate stock values. This is also the case in terms of the ability to predict stock prices. When comparing the two methods that were discussed earlier, this is the situation that arises. One can observe that there is a discernible difference between the two methods that are being applied in this situation. The first approach achieved an accuracy rate of 91.27%, while the second algorithm achieved a rate of 90.17%. Both methods were successful in achieving their respective goals. Both of the strategies were successful in achieving their respective goals, therefore neither of them should be considered failure. The results of the independent sample T-test make it possible to reach the conclusion that there is a difference between the two algorithms that is statistically significant. This conclusion may be reached by taking into consideration the findings of the evaluation. It is possible to arrive at this conclusion by taking into consideration the outcomes of the examination. This particular test yields a significant value of 0.012, which is lower than the cutoff value of 0.05. Taking note of the fact that this figure is lower than the threshold value is of the utmost importance. The Novel Random Forest Algorithm exhibits a higher level of accuracy and precision than the Convolutional Neural Network Algorithm does when it comes to the prediction of stock prices. This is because the Novel Random Forest Algorithm uses a stochastic algorithm. As a consequence of the algorithm’s capacity to forecast stock values, this has come about. The utilization of convolutional neural networks is employed for the goal of forecasting the values of stocks.