Stock Return Prediction Using Voting Regressor Ensemble Learning
Home Research Details
Ramadhan Ridho Arrohman, Riza Arifudin

Stock Return Prediction Using Voting Regressor Ensemble Learning

0.0 (0 ratings)

Introduction

Stock return prediction using voting regressor ensemble learning. Predict stock returns accurately using Voting Regressor ensemble learning in Python. This research achieves a low RMSE of 0.032523, offering real-time prediction capabilities.

0
5 views

Abstract

Abstract. The value of return on stock prices is often used in predicting profits in the process of buying and selling shares based on the calculation of the return on investment. The calculation of the value of return on stock prices can be predicted automatically at certain periods, both weekly and daily Purpose: The problem faced is determining a good algorithm for making predictions due to fluctuating data on stock prices making it difficult to predict. Methods: The stages carried out by the researcher include the data preprocessing stage and then proceed to the Exploratory Data Analysis (EDA) stage to get a pattern from the data, followed by the modeling stage on the data. This research was developed using the Python programming language where the models used to make predictions can be obtained in real-time. Result: The results obtained in this study show that the Voting Regressor has the best model with an error rate of 0.032523 using Root Mean Square Error (RMSE). The results of this study can be further developed to automatically predict stock return values in the future.


Review

The paper titled "Stock Return Prediction Using Voting Regressor Ensemble Learning" addresses a highly relevant and challenging problem within financial forecasting. The aim to develop a robust algorithm for predicting stock returns, particularly given the inherent volatility of stock price data, is a commendable objective. The application of ensemble learning, specifically a Voting Regressor, presents a theoretically sound approach to potentially enhance predictive accuracy and stability compared to single-model solutions. This is an area of significant interest for both academic research and practical application in investment strategies. From a methodological standpoint, the abstract outlines a structured approach beginning with data preprocessing, followed by Exploratory Data Analysis (EDA), and then the modeling phase. This systematic progression is appropriate for machine learning projects. However, the abstract's brevity in describing these stages leaves crucial details unaddressed. For instance, the specific base learners integrated into the Voting Regressor are not mentioned, nor are the particular techniques employed during data preprocessing or the key insights derived from EDA that informed the model's development. Elaboration on how the models can be obtained in "real-time" would also strengthen the description of the proposed system. The core finding indicates that the Voting Regressor yields the "best model" with a Root Mean Square Error (RMSE) of 0.032523. While an RMSE value is a standard metric for regression tasks, its practical significance in the context of stock return prediction is not discussed, making it difficult to fully appreciate the performance. Crucially, the abstract does not specify what other models were compared against the Voting Regressor to declare it "the best," which is a fundamental requirement for such a claim. Furthermore, the lack of information regarding the dataset used (e.g., its source, time period, specific stocks, and features) limits the ability to assess the generalizability and robustness of the reported results. Future work should detail these aspects, provide a comparative analysis with established benchmarks, and discuss the practical implications of the achieved error rate for real-world trading or investment decisions.


Full Text

You need to be logged in to view the full text and Download file of this article - Stock Return Prediction Using Voting Regressor Ensemble Learning from Recursive Journal of Informatics .

Login to View Full Text And Download

Comments


You need to be logged in to post a comment.