The Model of Artificial Neural Network and Nonparametric MARS Regression for Indonesian Composite Index

Devianto, Dodi; Permathasari, Putri; Yollanda, Mutia; Ahmad, Afridian Wirahadi

doi:10.1088/1757-899x/846/1/012007

Cited by 14 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, stock market data often exhibits non-linear patterns, which further complicates the forecasting process. In the paper [24] introduced approach for modeling the Indonesian Composite Index using artificial neural network (ANN) and nonparametric MARS regression. In the paper [25] researchers investigates the predictability of machine learning techniques for forecasting the trends of market index prices in the Korean stock markets.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Development neuro-fuzzy model to predict the stocks of companies in the electric vehicle industry

Barlybayev,

Zhetkenbay,

Karimov

et al. 2023

EEJET

View full text Add to dashboard Cite

Adaptive neuro-fuzzy inference system (ANFIS) it is a type of neural network that combines the strengths of both fuzzy logic and artificial neural networks. ANFIS is particularly useful in stock trading because it can handle uncertainty and imprecision in the data, which is common in stock market data. In stock trading, ANFIS can be used for a variety of purposes, such as predicting stock prices, identifying profitable trades, and detecting stock market trends. One of the key advantages of using ANFIS for stock trading is that it can handle both linear and non-linear relationships in the data. This is particularly useful in the stock market, where the relationships between different variables are often complex and non-linear. ANFIS can also be updated and retrained as new data becomes available, which allows it to adapt to changing market conditions. Therefore, the main hypothesis of this work is to understand whether it is possible to predict the dynamics of prices for stocks of companies in the electric vehicle (EV) sector using technical analysis indicators. The purpose of this work is to create a model for predicting the prices of companies in the EV sector. The technical analysis indicators were processed by several machine learning models. Linear models generally perform worse than more advanced techniques. Decision trees, whether fine or coarse, tend to yield poorer performance results in terms of RMSE, MSE and MAE. After conducting a data analysis, the ANFIS and Bayesian regularization back propagation Neural Network (BR-BPNN) models were seen to be the most effective. The ANFIS was trained for 2000 epochs which yielded a minimum RMSE of 5.90926

show abstract

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Development neuro-fuzzy model to predict the stocks of companies in the electric vehicle industry

Barlybayev,

Zhetkenbay,

Karimov

et al. 2023

EEJET

View full text Add to dashboard Cite

show abstract

“…It was seen that the model performed better on baselines on both the training and test datasets. Devianto et al (2020) used ANN and MARS methods for Indonesian Composite Index (ICI) prediction. As inputs to the prediction methods are given crude oil prices, interest rates, inflation, exchange rates, gold prices, Dow Jones price and Nikkei 225 index.…”

Section: Ijicc 164mentioning

confidence: 99%

An application on forecasting for stock market prices: hybrid of some metaheuristic algorithms with multivariate adaptive regression splines

Sabancı

Kılıçarslan

Adem

2023

IJICC

View full text Add to dashboard Cite

PurposeBorsa Istanbul 100 Index, known as BIST100, is the main indicator to measure the performance of the 100 highest stocks publicly traded in Borsa Istanbul concerning market and trading volume. BIST 100 index prediction is a popular research domain for its complex data structure caused by stock price, commodity, interest rate and exchange rate effects. The study proposed hybrid models using both Genetic, Particle Swarm Optimization, Harmony Search and Greedy algorithms from metaheuristic algorithms approach for dimension reduction, and MARS for prediction.Design/methodology/approachThis paper aims to model in the simplest way through metaheuristic algorithms hybridized with the MARS model the effects of stock, commodity, interest and exchange rate variables on BIST 100 during the Covid-19 pandemic period (in the process of closing) between January 2020 and June 2021.FindingsThe most suitable hybrid model was chosen as PSO & MARS by calculating the RMSE, MSE, GCV, MAE, MAD, MAPE and R2 measurements of training, test and overall dataset to check every model's efficiency. Empirical results demonstrated that the proposed PSO & MARS hybrid modeling procedure gave results both as good as the MARS model and a simpler and non-complex model structure.Originality/valueUsing metaheuristic algorithms as a supporting tool for variable selection can help to identify important independent variables and contribute to the establishment of more non-complex models.ing, test and overall dataset to check every model's efficiency.

show abstract

“…In modeling the Composite Stock Price Index, there are several factors that influence the Composite Stock Price Index, namely interest rates, inflation, crude oil prices, gold prices, and currency exchange rates. This study used the ANN model to build the Composite Stock Price Index modeling [21]. The research about neural networks was created again for analyzing the further application using ANN [22].…”

Section: Introductionmentioning

confidence: 99%

The soft computing FFNN method for adjusting heteroscedasticity on the time series model of currency exchange rate

Devianto

Yollanda

Maiyastri

et al. 2023

Front. Appl. Math. Stat.

Self Cite

View full text Add to dashboard Cite

IntroductionTime series models on financial data often have problems with the stationary assumption of variance on the residuals. It is well known as the heteroscedasticity effect. The heteroscedasticity is represented by a nonconstant value that varies over time.MethodsThe heteroscedasticity effect contained in the basic classical time series model of Autoregressive Integrated Moving Average (ARIMA) can adjust its residuals as the variance model by using Generalized Autoregressive Conditional Heteroscedasticity (GARCH). In improving the model accuracy and overcoming the heteroscedasticity problems, it is proposed a combination model of ARIMA and Feed-Forward Neural Network (FFNN), namely ARIMA-FFNN. The model is built by applying the soft computing method of FFNN to replace the variance model. This soft computing approach is one of the numerical methods that can not be only applied in the theoretical subject but also in the data processing.ResultsIn this research, the accuracy of the time series model using the case study of the exchange rate United States dollar-Indonesia rupiah with a monthly period from January 2001 to May 2021 shows that the best accuracy of the possible models is the model of ARIMA-FFNN, which applies soft computing to obtain the optimal fitted parameters precisely.DiscussionThis result indicates that the ARIMA-FFNN model is better used to approach this exchange rate than the rest model of ARIMA-GARCH and ARIMA-GARCH-FFNN.

show abstract

The Model of Artificial Neural Network and Nonparametric MARS Regression for Indonesian Composite Index

Cited by 14 publications

References 5 publications

Development neuro-fuzzy model to predict the stocks of companies in the electric vehicle industry

Development neuro-fuzzy model to predict the stocks of companies in the electric vehicle industry

An application on forecasting for stock market prices: hybrid of some metaheuristic algorithms with multivariate adaptive regression splines

The soft computing FFNN method for adjusting heteroscedasticity on the time series model of currency exchange rate

Contact Info

Product

Resources

About