Steel Price Forcasting Using Long Short-Term Memory Network Model

Cetin, Kemal; Aksoy, Serdar; İşeri, İsmail

doi:10.1109/ubmk.2019.8907015

Cited by 10 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The study results showed that the GMDH forecasting model is significantly better than other forecasting models and that the GMDH technique can forecast the price of iron ore with a higher degree of accuracy than other techniques analyzed. Cetin et al (2019) developed a steel price forecasting method using the long short-term memory (LSTM) network model, which is an adapted model of recurrent neural network architecture, and obtained the best forecasting result from the forward five-day forecasting model with high correlation coefficient R. For their forecast of iron sale price, Jian Ming et al (2016) looked into different data analysis methods and used artificial neural networks and automatic regression moving average as forecasting models. They concluded that the combined forecasting model is effective and feasible, and the results of this forecast can provide effective support for companies in their strategic decisionmaking.…”

Section: Literature Reviewmentioning

confidence: 99%

Determination of iron procurement strategy for manufacturing companies

Apanovych,

Prágr

2023

JESI

View full text Add to dashboard Cite

The objective of this paper is to evaluate the price development of iron (steel rebar and hot rolled coil steel) on commodity exchanges, to determine the dependence of the price of iron on prices of other major commodities (crude oil and natural gas), to forecast its future development and to propose a particular iron procurement strategy for manufacturing companies in the South Bohemian Region until the end of 2028. The content analysis method was selected to evaluate the price development. It was also used to assess the dependence of iron prices on other major commodities, which was considered using the correlation analysis method. The artificial neural network method, multilayer perceptron networks, was selected and used to forecast future price development. All calculations are performed using Statistica software (version 13). Linear regression is conducted using different functions, with 1,000 neural structures being generated each time, out of which 5 structures showing the best characteristics are selected. These are retained to forecast future prices for the 2023-2028 period in three experiments. Results are presented in tables and graphs processed in Microsoft Excel. Based on the selected variants of future steel price forecasting, a specific iron procurement strategy can be recommended for manufacturing companies in the South Bohemian Region until the end of 2028.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Determination of iron procurement strategy for manufacturing companies

Apanovych,

Prágr

2023

JESI

View full text Add to dashboard Cite

show abstract

“…They showed a spillover effect between spot and future market in wire rod, coking coal, coke, and silicomanganese. Another research has come from Cetin, Aksoy and Iseri (2019), which tried to forecast steel prices using the long short-term memory network model (LSTM). They used ten years' steel price data obtained from LME to forecast steel prices.…”

Section: Literature Reviewmentioning

confidence: 99%

Forecasting of the U.S. Steel Prices with LVAR and VEC Models

Adli¹,

Şener²

2021

berj

View full text Add to dashboard Cite

Base metal prices, especially steel, play a significant role in industrial economics, making them worth knowing about future values. In most cases, we expect superior performance from multivariate forecasting models comparing univariate methods due to the involvement of explanatory variables in the system. Standard vector auto regressive model can only capture short-run dynamics because of the differencing process for non-stationary series that eliminates the possible long-run relationship. Instead, performing non-stationary series on levels through the vector auto-regressive framework does not suffers such loss. Moreover, the vector error correction model can define both short-term and long-run dynamics explicitly. These models can yield more robust forecasts in the mid-term and long-term by investigating short-run and long-run relationships simultaneously. The current study aims to perform an out-of-sample forecast for the United States steel prices index 18 months ahead using cointegrated variables. The results suggest that the non-stationary vector auto-regressive model outperforms the vector error correction model regarding mean absolute percentage error and root mean square error as forecast accuracy measures.

show abstract

“…3. The model has been created by employing Long short-term memory cells (LSTM), which provide a chain of outputs rather than providing a single output [17].…”

Section: Algorithm Steps Of Rnnmentioning

confidence: 99%

Artificial Intelligence for anomaly detection by employing deep learning strategies in IoT networks using the trendy IoT-23 big data from Google's Tensorflow2.2

Kanimozhi

Jacob

2021

Preprint

View full text Add to dashboard Cite

Although numerous profound learning models have been proposed, this research article contributed to symbolize the investigation of artificial deep learning models on sensible IoT gadgets to perform online protection in IoT network traffic by using the realistic IoT-23 dataset. This dataset is a recent network traffic dataset generated from the real-time network traffic data of IoT appliances. IoT products are utilized in various program applications such as home, commercial, mechanization, and various forms of wearable technologies. IoT security is more critical than network security because of its massive attack surface and multiplied weak spots of IoT gadgets. Universally, the general amount of IoT gadgets conveyed by 2025 is foreseen to achieve 41600 million. Henceforth, IoT anomaly detection systems based on the realistic Iot-23 big data for detecting IoT-based attacks on the artificial neural networks of Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Multilayer perceptron (MLP) in IoT- cybersecurity has implemented and executed in this research article. As a result, Convolutional Neural Networks produces an outstanding performance of metric accuracy score is 0.998234, and minimal loss function is 0.008842, compare to Multilayer perceptron and Recurrent Neural Networks in IoT Anomaly Detection. Also generated well-displayed graph plots of Model_Accuracy, Learning curve of artificial Intelligence deep learning algorithms such as MLP, CNN, and RNN.

show abstract

Steel Price Forcasting Using Long Short-Term Memory Network Model

Cited by 10 publications

References 12 publications

Determination of iron procurement strategy for manufacturing companies

Determination of iron procurement strategy for manufacturing companies

Forecasting of the U.S. Steel Prices with LVAR and VEC Models

Artificial Intelligence for anomaly detection by employing deep learning strategies in IoT networks using the trendy IoT-23 big data from Google's Tensorflow2.2

Contact Info

Product

Resources

About