Non-ferrous metals are indispensable industrial materials and strategic supports of national economic development. The price forecasting of non-ferrous metals is critical for investors, policymakers, and researchers. Nevertheless, an accurate and robust non-ferrous metals price forecasting is a difficult yet challenging problem due to severe fluctuations and irregular cycles in the metal price evolution. Motivated by the ”Divide-and-Conquer” principle, we present a novel hybrid deep learning model, which combines the VMD (variational mode decomposition) method and the LSTM (long short-term memory) network to construct a forecasting model in this paper. Here, the VMD method is firstly employed to disassemble the original price series into several components. The LSTM network is used to forecast for each component. Lastly, the forecasting results of each component are aggregated to formulate an ultimate forecasting output for the original price series. To investigate the forecasting performance of the proposed model, extensive experiments have been executed using the LME (London Metal Exchange) daily future prices of Zinc, Copper and Aluminum, and other six state-of-the-art methods are included for comparison. The experiment results demonstrate that the proposed model has superior performance for non-ferrous metals price forecasting.

Non-ferrous metals price forecasting based on variational mode decomposition and LSTM network

In recent years, the investors pay major attention to invest in gold market ecause of huge profits in the future. Gold is the only commodity which maintains ts value even in the economic and financial crisis. Also, the gold prices are closely elated with other commodities. The future gold price prediction becomes the warning ystem for the investors due to unforeseen risk in the market. Hence, an accurate gold rice forecasting is required to foresee the business trends. This paper concentrates on orecasting the future gold prices from four commodities like historical data’s of gold rices, silver prices, Crude oil prices, Standard and Poor’s 500 stock index (S&P500) ndex and foreign exchange rate. The period used for the study is from 1st January 000 to 31st April 2014. In this paper, a learning algorithm for single hidden layered eed forward neural networks called Extreme Learning Machine (ELM) is used which as good learning ability. Also, this study compares the five models namely Feed orward networks without feedback, Feed forward back propagation networks, Radial asis function, ELMAN networks and ELM learning model. The results prove that he ELM learning performs better than the other methods.

/pdf/forecasting-gold-prices-based-on-extreme-learning-machine-lxee006xab.pdf

Forecasting Gold Prices Based on Extreme Learning Machine

Gold price forecasting has been a hot issue in economics recently. In this work, wavelet neural network (WNN) combined with a novel artificial bee colony (ABC) algorithm is proposed for this gold price forecasting issue. In this improved algorithm, the conventional roulette selection strategy is discarded. Besides, the convergence statuses in a previous cycle of iteration are fully utilized as feedback messages to manipulate the searching intensity in a subsequent cycle. Experimental results confirm that this new algorithm converges faster than the conventional ABC when tested on some classical benchmark functions and is effective to improve modeling capacity of WNN regarding the gold price forecasting scheme.

/pdf/research-on-wnn-modeling-for-gold-price-forecasting-based-on-m6qavhn8ov.pdf

Research on WNN modeling for gold price forecasting based on improved artificial bee colony algorithm

Accurate gold price prediction is highly essential for economic and currency markets. Thus, the intelligence prediction models need to be applied to price prediction. On the basis of long-term collected daily gold, the study proposes a novel genetic algorithm regularization online extreme learning machine (GA-ROSELM), to predict gold price data which collected from public websites. Akaike Information Criterion (AIC) is introduced to build the eight input combinations of variables based on the silver price of the previous day (Silver_D1), Standard & Poor. The 500 indexes (S&P_D1), the crude oil price (Crude_D1), and the gold price of the previous 3 days (Gold_D1, Gold_D2, Gold_D3). Eight optimal variable models are established, and the final input variables are determined according to the minimum AIC value. The proposed model (GA-ROSELM) solve the problem that OS-ELM model which is easy to generate singular matrices, meanwhile, experiments demonstrate this model performs better than ARIMA, SVM, BP, ELM and OS-ELM in the gold price prediction experiment. On the test set, the root means square error of this model (GA-ROSELM) prediction compared with five other models which decreased by 13.1%, 22.4%, 53.87%, 57.84% and 37.72% respectively. In summary, the results clearly confirm the effectiveness of the GA-ROSELM model.

Gold price forecasting research based on an improved online extreme learning machine algorithm

Gold price fluctuation trend prediction is an important issue in the financial world. Even small improvements in predictive performance can make lots of profits. In order to improve the prediction, various factors were considered in related literatures, such as US dollar index (USDX), the crude oil price (COP), Dow Jones Industrial Average (DJIA), the CPI of US (USCPI), the prices of US ten year bond futures (US10BFP), the Hang Seng Index (HIS) and the Standard & Poor’s 500 Index (S&P500), etc. However, the more factors should be considered, the more difficult data can be gathered. This paper used the random forest method to predict the trend of fluctuations of the gold price. Our predictions are one month ahead. Extensive experiments based on real world data were conducted. Our findings show that (1) the random forest is a powerful method to predict the trends of fluctuations of the gold price and (2) the results also validated that, by using the random forest algorithm, there were only two factors must be considered to ensure the performance of the prediction, which were DJIA and S&P500.

Gold Price Forecasting and Related Influence Factors Analysis Based on Random Forest

This paper predicts good price based on RBF neural network employing hybrid fuzzy clustering algorithm. PCA technique has been used to integrate the 6 parameter dependent sub-variables of each TI (Technical Indicators, include MA, ROC, BIAS, D, K), which has been originated from the gold price before, and the results act as input. By employing a new hybrid fuzzy clustering algorithm, which is proposed by Antonios and George [10], K-Mean clustering algorithm and RBE algorithm, the predictions of price are yielded for each interval-n model. n refers to the number of predictions achieved by 1 operation. The most important conclusion indicates that the hybrid fuzzy clustering algorithm is superior to the general RBF central vector selecting algorithm mentioned above, in the aspects of MSE, P-Accuracy Rate and ROC.

Gold Price Forecasting Based on RBF Neural Network and Hybrid Fuzzy Clustering Algorithm

Multi-scale and multi-layer perceptron hybrid method for bearings fault diagnosis

This work provides a general analysis method for the crack detection in shales. The acoustic emission (AE) testing with data recovery is proposed for determining the crack modes and positions in the test and analysis process of the shale fracturing experiment. A fracturing and in situ AE monitoring system is constructed to collect the experimental data in at least six channels for the crack detection, and the source positions output from AE testing represent the positions of cracks. Due to some uncontrollable reasons, such as the poor coupling between sensors and sample and the sudden failure of the sensors, some parts of experimental data are missing during the experiments. Therefore, a data recovery neural network algorithm based on wavenet model is introduced to reconstruct the missing parts of experimental data in the waveforms. Since the accuracy of data recovery is not satisfying based on the collected experimental data, the interpolation of experimental data is performed to refine the data which can obviously improve the accuracy of data recovery. After all the required experimental data have been recovered, the crack mode for each crack can be determined based on the moment tensor analysis. This analysis method can be extensively applied to the shale crack detection. 

Fengyi Zhang

Papers

Gold Price Forecasting Based on RBF Neural Network and Hybrid Fuzzy Clustering Algorithm

Multi-scale and multi-layer perceptron hybrid method for bearings fault diagnosis

Shale crack identification based on acoustic emission experiment and wavenet data recovery