Predicting Closed Price Time Series Data Using ARIMA Model

Wadi, S. Al; Almasarweh, Mohammad Salameh

doi:10.5539/mas.v12n11p181

Cited by 43 publications

(30 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, to apply ARIMA statistical technique, there are many constraints such as making data stationary or linearizing by taking the exponential of data. In addition, this method is generally poor at predicting turning points (Meyler, Kenny, & Quinn, 1998) (Wadi, 2018) which happens in our case.…”

Section: Theoretical Background Of the Algorithmsmentioning

confidence: 67%

Günlük Bitcoin Değerini Tahmin Etmek İçin İstatistiksel ve Makine Öğrenimi Algoritmalarının Karşılaştırılması

Aygun¹,

Gunay²

2021

European Journal of Science and Technology

View full text Add to dashboard Cite

Increasing fluctuations in pricing and having great profit potential, utilization in advanced machine learning technologies to make robust predictions of cryptocurrencies especially bitcoin have attracted great attention in recent years. In this study, various statistical techniques; Moving Average Analysis and Autoregressive Integrated Moving Average and machine learning (ML) techniques; Artificial Neural Network, Recurrent Neural Network (RNN) and Convolutional Neural Network have been conducted and compared to predict the future value of Bitcoin cryptocurrency price. They have been applied for the univariate time series analysis with a window size of 32. To prove the usefulness of ML algorithms, and to show that the results of RNN is a better, mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) indicators have been applied. The study revealed that recurrent neural network yields better results than other methods in predicting daily Bitcoin price in terms of MSE, MAE and MAPE metrics. Besides, Wilcoxon-Mann-Whitney nonparametric statistic test is applied to test the performance between ARIMA and machine learning algorithms.

show abstract

Section: Theoretical Background Of the Algorithmsmentioning

confidence: 67%

Günlük Bitcoin Değerini Tahmin Etmek İçin İstatistiksel ve Makine Öğrenimi Algoritmalarının Karşılaştırılması

Aygun¹,

Gunay²

2021

European Journal of Science and Technology

View full text Add to dashboard Cite

show abstract

“…Many well-known times series forecasting methods have been used for this reason. Autoregressive Integrated Moving Average (ARIMA) models have been especially popular in the stock market's time series prediction [17,63]. Furthermore, hybrid methods exploiting similar approaches have also been introduced.…”

Section: Related Workmentioning

confidence: 99%

A Comparison of Contemporary Methods on Univariate Time Series Forecasting

Karanikola

Liapis

Kotsiantis

2021

Learning and Analytics in Intelligent Systems

View full text Add to dashboard Cite

In data science, time series forecasting is the process of utilizing past or present (known) observations of a target variable to make predictions about future (unknown) observations. Due to the usefulness of forecasting applications in numerous real-life problems, various Statistical and Machine Learning forecasting models have been proposed over recent years. The purpose of this chapter is to compare the performance of several contemporary forecasting models that are considered state of the art. These include Autoregressive Integrated Moving Average (ARIMA), Neural Basis Expansion Analysis (NBEATS), Probabilistic Time Series Modeling focusing on deep learning-based models and others. In the first section of this work a brief theoretical background of the methods is provided. Then, the experimental procedure is being described. For the comparison, 40 univariate time series of financial data that cover a 1-year period were used. A python repository of automated time series forecasting models (AtsPy) was exploited to run the experiments. For the final comparison three different metrics (RMSE, MAE and MAPE) were taken into consideration. The results of this extended experimental procedure are presented through various explanatory diagrams of the methods' performance in the final section.

show abstract

“…Wadi et al [1] found the best-fit ARIMA model for forecasting the closed price of Jordan's ASE, with p, d, and q parameters of 2, 1, and 1 correspondingly, and RMSE=4 . For the banking stock data of Jordan's ASE, the ARIMA p=1, d=1, and q=2 suited most with RMSE=1.4 Almasarweh and Alwadi [2].…”

Section: Literature Reviewmentioning

confidence: 99%

Forecasting non-linear WPI of manufacture of chemicals and chemical products in India: an MLP approach

Das¹,

Chakrabarti²

2021

IJATEE

View full text Add to dashboard Cite

Forecasting predicts/ estimates the future by taking into account historical data. It's an instrument of decision-making that assists companies/ enterprises/ institutions in managing uncertainties. It allows the business to set up goals and create a budget. Forecasting helps us to anticipate changes and therefore guide us towards data-driven strategies and reasoned decisions/ choices. It serves as a proactive rather than a reactive measure. There are several forecasting approaches for the univariate time series (TS) data, e.g. *Author for correspondence Auto-Regressive Integrated Moving Average (ARIMA) [1-3], exponential smoothing (ES) [4-6], Support Vector Regression (SVR) [7, 8, 9], neural approaches [10-12]. The recent studies show that the researchers employed these approaches for forecasting various TS data, e.g., stock prices [1, 2, 13], prices of agricultural products [4, 5, 6], price index [10, 14].India's chemical industry is highly diverse, covers a wide range of products, and has a large import and export base. More than two million people are working here. On the economic growth of India, this sector's contribution is notable. In the future, there exists a significant opportunity for the industry's business/ revenue growth.

show abstract

Predicting Closed Price Time Series Data Using ARIMA Model

Cited by 43 publications

References 17 publications

Günlük Bitcoin Değerini Tahmin Etmek İçin İstatistiksel ve Makine Öğrenimi Algoritmalarının Karşılaştırılması

Günlük Bitcoin Değerini Tahmin Etmek İçin İstatistiksel ve Makine Öğrenimi Algoritmalarının Karşılaştırılması

A Comparison of Contemporary Methods on Univariate Time Series Forecasting

Forecasting non-linear WPI of manufacture of chemicals and chemical products in India: an MLP approach

Contact Info

Product

Resources

About