Predicting the Link between Stock Prices and Indices with Machine Learning in R Programming Language

Abstract

This paper provides an in-depth analysis machine study of the relationship between stock prices and indices through machine learning algorithms. Stock prices are difficult to predict by a single financial formula because there are too many factors that can affect stock prices. With the development of computer science, the author now uses many computer science techniques to make more accurate predictions of stock prices. In this project, the author uses machine learning in R Studio to predict the prices of 35 stocks traded on the New York Stock Exchange and to study the interaction between the prices of four indices in different countries. Further, it is proposed to find the link between stocks and indices in different countries and then use the predictions to optimize the portfolio of these stocks. To complete this project, the author used Linear Regression, LASSO, Regression Trees, Bagging, Random Forest, and Boosted Trees to perform the analysis. The experimental results show that the MRDL deep multiple regression model proposed in this paper predicts the closing price trend of stocks with a mean square error interval [0.0043, 0.0821]. Additionally, 80% of the proposed DMISV, KDJSV, MACDV, and DKB stock buying and selling strategies have a return greater than 10%. The experimental results validate the effectiveness of the proposed buying and selling strategies and stock price trend prediction methods in this paper. Compared with other algorithms, the accuracy of the algorithm in this study is increased by 15%, and the efficiency of prediction is increased by 25%.

A novel approach for candlestick technical analysis using a combination of the support vector machine and particle swarm optimization

“…For example. The other researcher (Cao, 2021) Heuristics and metaheuristic algorithms play an important role in these methods, and their extensive use in recent years indicates how successful they have been. Another study (Shen et al, 2020) has highlighted that using methods of ANNs and SVM can simply find the hidden framework in the prediction via the self-learning process.…”

“…For example. The other researcher (Cao, 2021) used linear regression, Least Absolute Shrinkage and Selection Operator (LASSO), regression trees, bagging, random forest and boosted tress to analyze data and predict the stock price movement of 35 companies on the New York stock exchange. Simultaneously with the development of artificial intelligence methods, nonlinear methods of machine learning have been proposed.…”

Predicting Shariah Stock Market Indices with Machine Learning: A Cross-Country Case Study

“…Using machine learning techniques allows researchers to improve stock price forecasts and gain a deeper insight into the correlations among index prices across different countries (Cao, 2023). Previous academic studies on stock markets have predominantly employed intricate methods to predict stock price fluctuations, considering the factors influencing them and the intricate nature of financial markets (Xiao et al, 2021).…”

Prediction of Peruvian companies' stock prices using Machine Learning

“…We have to have as a basis what independent variables we are going to use, since these are the ones that will predict the future behavior of the trends that could adopt the shares; there is a different point of view between what types of independent variables should be used for the prediction of shares, in its majority are usually used characteristics of a share such as its closing price, opening, volume and volatility as considered by Umer (2019), who employed them and demonstrated their effectiveness in a stock prediction system using ML algorithms; but more specifically momentum indicators are usually used with Support Vector Machine (SVM) and its variants such as Support Vector Regression (SVR); the former mostly used for classification and the latter for regression. We quote Cao (2021), who relied on momentum indicators to forecast the price of a stock used only three momentum indicators, MACD, KDJ, and DMI, his prediction model obtained a higher accuracy by 25% compared to other models. But it is necessary to emphasize that his model is quite different from this one since his model is mixed and makes use of LASSO, random forests, R language, among others.…”

“…Between the use of Machine Learning (ML) and artificial neural networks (ANN) for stock prediction, Cao (2021) states that the former involves models that are becoming increasingly complex due to the number of variables involved and artificial neural networks and decision trees work better for prediction. In the same way, there are other positions…”