Dataset Of Prices Research Articles

Advanced Deep Learning-Based Predictive Modelling for Analyzing Trends and Performance Metrics in Stock Market

Objective: This study's main goal is to investigate how deep learning approaches may be used to analyze stock market performance. The complex patterns and nonlinear interactions present in stock market data may be difficult to completely capture using traditional approaches, which are mostly based on statistical models.
 Methodology: Our work uses a large dataset of historical stock prices, macroeconomic indices, and other crucial financial factors to address this. Simple Moving Averages (SMA) are one of the feature engineering approaches that are used to combine fundamental and technical indicators. To capture the temporal dynamics of the stock market, the study goes further into a variety of deep learning architectures, including as long short-term memory (LSTM) networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs).
 Findings: The results show that thorough feature engineering combined with deep learning approaches may effectively capture the complexity of the stock market and provide forecasts that are more accurate.
 Implications: This highlights how deep learning may revolutionize financial market research and points to a paradigm change toward more trustworthy instruments for investors and decision-makers.

Twin extreme learning machine based on heteroskedastic Gaussian noise model and its application in short-term wind-speed forecasting

Extreme learning machine (ELM) has received increasingly more attention because of its high efficiency and ease of implementation. However, the existing ELM algorithms generally suffer from the drawbacks of noise sensitivity and poor robustness. Therefore, we combine the advantages of twin hyperplanes with the fast speed of ELM, and then introduce the characteristics of heteroscedastic Gaussian noise. In this paper, a new regressor is proposed, which is called twin extreme learning machine based on heteroskedastic Gaussian noise (TELM-HGN). In addition, the augmented Lagrange multiplier method is introduced to optimize and solve the presented model. Finally, a significant number of experiments were conducted on different data-sets including real wind-speed data, Boston housing price dataset and stock dataset. Experimental results show that the proposed algorithms not only inherits most of the merits of the original ELM, but also has more stable and reliable generalization performance and more accurate prediction results. These applications demonstrate the correctness and effectiveness of the proposed model.

Incremental nonlinear trend fuzzy granulation for carbon trading time series forecast

In addition to its important economic value, carbon trading is also an important tool in international politics and diplomacy. Carbon price forecast accuracy has far-reaching implications for economic development and the environment. Few existing studies have been more accurate in predicting carbon prices over longer periods. In this paper, the incremental Gaussian nonlinear trend fuzzy granulation method and the Gaussian nonlinear trend fuzzy granulation method are innovatively proposed to predict carbon prices. This study first converts carbon prices into incremental granulation time series. A time-varying core line is added to produce nonlinear trend granulation on the foundation of linear trend granulation. The nonlinear trend and residual information are then predicted using the DeeAR network, respectively, and the final prediction result is obtained by adding the predicted values for each. Moreover, a new evaluation index, the comprehensive evaluation of RMSE, MAE, and MAPE as three indicators, is proposed to consider the accuracy of the evaluation index more comprehensively and reliably. The results show that the prediction method has the smallest error in long-term prediction compared with other models. The daily closing price datasets of carbon exchanges published in Shenzhen and Beijing are used to validate the efficacy of this methodology.

A ternary-frequency cryptocurrency price prediction scheme by ensemble of clustering and reconstructing intrinsic mode functions based on CEEMDAN

Cryptocurrency, particularly Bitcoin, is a significant financial asset for investors, but predicting its price is challenging due to its volatile and erratic nature. In this study, we suggest a novel ternary-frequency (TF) prediction scheme for Bitcoin prices, which combines complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), a time series clustering method, and the reconstruction of intrinsic mode functions (IMFs). In the proposed scheme, CEEMDAN was utilized to decompose Bitcoin’s daily price into IMFs, then prototypes of time series clustering were used to construct robust ensemble clusters. The IMFs in the ensemble clusters were reconstructed into ensemble time series and then identified as three different frequencies, which were respectively used in a prediction model to generate different predicted values, and then aggregated to produce the final prediction results. To generate three different TF Bitcoin price prediction schemes, this study employed three prominent prediction algorithms: autoregressive integrated moving average with exogenous variables (ARIMAX), multivariate adaptive regression splines (MARS), and extreme gradient boosting (XGB); these resulted in three distinct models, named TF-ARIMAX, TF-MARS, and TF-XGB. Empirical results from the two daily Bitcoin and one daily Ethereum closing price datasets showed that the proposed TF prediction scheme outperformed other benchmark approaches. Moreover, among the three TF models, TF-MARS produced superior prediction accuracy compared to both TF-ARIMAX and TF-XGB models, and proved to be an effective alternative for cryptocurrency price prediction.

A New Algorithm for Large-Scale Geographically Weighted Regression with K-Nearest Neighbors

Geographically weighted regression (GWR) is a classical method for estimating nonstationary relationships. Notwithstanding the great potential of the model for processing geographic data, its large-scale application still faces the challenge of high computational costs. To solve this problem, we proposed a computationally efficient GWR method, called K-Nearest Neighbors Geographically weighted regression (KNN-GWR). First, it utilizes a k-dimensional tree (KD tree) strategy to improve the speed of finding observations around the regression points, and, to optimize the memory complexity, the submatrices of neighbors are extracted from the matrix of the sample dataset. Next, the optimal bandwidth is found by referring to the spatial clustering relationship explained by K-means. Finally, the performance and accuracy of the proposed KNN-GWR method was evaluated using a simulated dataset and a Chinese house price dataset. The results demonstrated that the KNN-GWR method achieved computational efficiency thousands of times faster than existing GWR algorithms, while ensuring accuracy and significantly improving memory optimization. To the best of our knowledge, this method was able to run hundreds of thousands or millions of data on a standard computer, which can inform improvement in the efficiency of local regression models.

Determining the Best Model among Candidate Machine Learning Models for Chicago Suburb House Price Data

With the development of the society, there is an increasing need of predicting the house price in order to purchase properties economically. Myriads of machine learning methods have been developed to achieve this goal. In this paper, we narrow our focus on three types of machine learning methods-Linear Regression, Polynomial Regression, and Neural Network (Multilayer Perceptron Regressor) and train all of them on Chicago suburb house price dataset and employ all of them to make predictions. Performance is evaluated using mean squared error (MSE) and R square (R2) metrics. Preliminary experimental results demostrate that Neural Network outperforms the other candidate methods in all cases. Polynomial Regression of degree 2 outperforms Linear Regression in most cases but performs arbitrarily bad in worst cases. Therefore, Neural Network (MLP Regressor) is the best method for predicting Chicago suburb house price.

Super learner ensemble model: A novel approach for predicting monthly copper price in future

Companies and governments dependent on copper mining need to be able to predict copper prices in order to make important decisions. Despite the nonlinear and nonstationary nature of copper prices, their periods may vary as they fluctuate due to potential growth, cyclical fluctuations and errors. A trend-cycle refers to the combination of trend and cyclical components. Trend-cycles are characterized by different characteristics, which are crucial to making predictions. Therefore, this study focuses on developing and proposing a novel model based on an ensemble machine learning technique to predict monthly copper prices in the future by using different soft computing methods, including multi-layer perception (MLP) neural network, support vector regression (SVR), and extreme gradient boosting (XGBoost). The monthly copper price dataset from August 2001 to August 2021 was gathered for this aim based on the 14 effective parameters. These parameters were selected based on the suggestions of previous research. The main novelty of this study is the development most accurate model to predict monthly copper prices using Cubist algorithm-based super learner model as the new predictive system. The results indicated that the proposed super learner models outperformed of MLP, SVR, and XGBoost models based on the determination coefficient (R-squared), value account for (VAF), root mean square of errors (RMSE), Accuracy (Acc) and Mean Absolute Relative Error (MARE). A comprehensive comparison of different artificial intelligence models demonstrates that MLP neural network is the best model for predicting monthly copper prices. However, the standalone models involving MLP, SVR, and XGBoost, presented higher error with an RMSE in the interval of [278.3826 - 502.6946], and MARE in the interval of [0.056 - 0.1277]. Hence, Cubist-based super learner can be employed as a reliable system to predict monthly copper prices in the future. Besides, this study presents a rational mathematical model based on gene expression programming (GEP) for copper price prediction in future and for use by other researchers. Noteworthy, the final step of the study was sensitivity analysis conducting, which the results revealed that “lead price” and “euro to USD” parameters have respectively the lowest and highest impact on the monthly copper price.

LONG- AND SHORT-TERM EVOLUTION OF SALE PRICES OF AGRICULTURAL PRODUCTS IN UKRAINE IN 2010-2021

The price is an indicator that accumulates information about the cost of production, balance between supply and demand, its quality evaluation by consumers, the variety of offer by manufacturers and other characteristics. The price is formed not only as a mathematically calculated value depending on the cost price or accompanying costs, but it considers the market situation. Prices on agricultural products are influenced by such industry specific as production seasonality.
 The source data base was analyzed to study prices evolution for some agricultural products in Ukraine. In particular, the features of changes in price indicators were revealed and described for fruit, berries, potatoes, grains, legumes, and oil crops.
 Vegetable price data set was analyzed to reconstruct evolution of price fluctuations for the period of January 2010 - December 2021. Decomposing method was applied to extract trend, seasonal and random components from time series. It allowed to build short- and long-term tendencies on the base of its fluctuations. A multiplicative model was approximated to understand dynamics of price index and reveal its behavior in impact circumstances of nature and economic factors. Price fluctuations for agricultural products is presented monthly and in years. It helped to describe long-term trend of price evolution. Moreover, modelling let us to predict values for 2022 and 2023. Forecasted values were compared with factual data from official statistical sources. 
 According to results of analysis predicted dynamics almost completely repeated real tendency, in seasonality. Nevertheless, prices of 2022-2023 years were influenced by Russian invasion consequences. Prices soared over the predicted values. That happened because of destruction of the logistics for agricultural products supply, loss of farm assets, contamination of land with explosive substances, rise of inflation, increase of costs and demand on deficient goods, shortening of products and raw supply. At the same time, it is demonstrated that prices of products of so-called "borscht set" have been constantly increasing since 2013. That was caused by inflation and poor harvests. Mentioned factors led to that certain vegetables were imported from abroad.

The performance analysis of stock predication based on recurrent neural network

The stock exchange is unpredictable, and the stock price seems unpredictable. However, with the continuous development of the deep learning model's ability to deal with massive data, forecasting stock prices has become feasible and has reference value for investors. Many factors affect the stock price, and it is a great challenge to define these factors' influence on the price clearly. This paper selects multi-features stock price data sets of different companies. Because of the superiority of recurrent neural networks in dealing with time series problems, this paper compares and analyzes the experimental results of four models, namely Long Short Term Memory, Bi-directional Long Short-Term Memory, Gate Recurrent Unit, and Bi-directional Gate Recurrent Unit, and concludes that the BiLSTM model is the most outstanding one. At the same time, the prediction accuracy under different feature numbers is compared. The experimental results show that the stock price forecasting model with multi-features shows good performance, but the noise brought by it can't be ignored.

Deriving Controllable Local Optimal Solutions through an Environment Parameter Fixed Algorithm

This paper addresses the challenge of optimizing objective functions in engineering problems influenced by multiple environmental factors, such as temperature and humidity. Traditional modeling approaches often struggle to capture the complexities of non-ideal situations. In this research, we propose a novel approach called the Environment Parameter Fixed Algorithm (EPFA) for optimizing the objective function of a deep neural network (DNN) trained in a specific environment. By fixing the environmental parameters in the DNN defined objective function, we transform the original optimization problem into a control parameter optimization problem. We integrate EPFA-CLS (Controllable local-Optimal Solution) with Gradient Descent and algorithms such as Adagrad to obtain the optimal solution. To demonstrate the concept, we apply our approach to an optimal course model and validate it using optimal course and Boston house price datasets. The results demonstrate the effectiveness of our approach in handling optimization problems in complex environments, offering promising outcomes for practical engineering applications.

Consistent subsets: Computing the Houtman–Maks index in Stata

The Houtman–Maks index is a measure of the size of a violation of utility-maximizing (that is, rational) behavior. In this article, we introduce the command hmindex, which calculates the Houtman–Maks index for a dataset of prices and observed choices of a consumer. The command is illustrated with an empirical application.

Mobile Phone Price Classification Using Machine Learning

Smartphones are becoming more and more important for people day by day. With the development of technology, telephones are used in many areas from daily life to business life. It does not only fulfil the function of calling someone. It also makes it possible to connect to the internet and read mail while away from the computer. For this reason, the features of the mobile phone are an important factor when purchasing a mobile phone. People who actively use the phone pay more attention to feature selection. When buying a cell phone, price-performance comparison is made. Phone features are considered as performance. There is no exact method for determining the price. Price estimation can be done with the use of machine learning algorithms. Many studies have been conducted on this subject in the literature. There are still ongoing studies on which machine learning algorithm is the most appropriate. In order to contribute to this issue, a price prediction study is conducted on different machine learning algorithms. Using a dataset of phone prices and features from Kaggle, 4 different models with 20 features are tackled. As a result, the highest value is obtained from Support Vector Machine with an accuracy value of 0.9616.

JUE Insight: The impact of the school admission restriction policy on the housing market in Shanghai

This study explores the influence of a regulation of informal school choice on the housing market in Shanghai to estimate the significance of loopholes in the school district system. The policy limited the priority for enrollment in a public elementary schools given to house owners in the school's district so that each housing property is given only one priority every five years; hence, informal acquisition of priorities through frequent resale of houses is limited. From the dataset of individual housing prices in Shanghai, we show that house price within the school districts of good schools increases after the policy. In contrast, house price decreases in areas that are neighboring the school but outside its school district because they are called “babysitting communities” and provide houses to live in for households who resell their houses earlier than graduation of their children. We also implement event study analysis to estimate time-varying influences of the policy, to show that the significant price increase occurs immediately after the policy implementation and shrinks a little in the short run.

Comparison of Real Estate Price Prediction Based on LSTM and LGBM

Housing price prediction is one of the widely discussed topics, and the application of machine learning and deep learning models to housing price prediction is a research hotspot. Exploring which models are suitable for predicting real housing price datasets has significant implications for guiding government and homebuyers' decision-making. In this study, the LSTM and LightGBM models were selected as research objects, and the suitability of the models was explored and compared using the second-hand housing price dataset in Beijing. Based on the analysis, in the task of pure time series prediction based on historical housing prices, the LSTM model had a better fit (R2=0.91), while in the task of housing price prediction based on multiple influencing factors, the LightGBM model had better comprehensive evaluation index results (R2=0.53). Both models can be used to predict pure time series, but the LSTM model is not suitable for predicting multi-factor input models that are not time series.

Does climate change affect economic data?

This paper derives the seasonal factors from the US temperature, gasoline price, and fresh food price data sets using the Kalman state smoother and the principal component analysis. Seasonality in this paper is modeled by the autoregressive process and added to the random component of the time series. The derived seasonal factors show a common feature: their volatilities have increased over the last four decades. Climate change is undoubtedly reflected in the temperature data. The three data sets' similar patterns from the 1990s suggest that climate change may have affected the prices' volatility behavior.

Dream House Price Predictor

Abstract: The dream house price predictor project aims to build a machine learning model that can predict the selling price of a house based on various features such as location, number of bedrooms, square footage, and other relevant factors. The model will be trained on a dataset of historical housing prices and features, and will use regression techniques to make predictions on new, unseen data. The project will also explore the impact of different features on house prices and provide insights into which factors are the most important in determining the value of a property. The goal of the project is to provide a tool for homebuyers, sellers, and real estate professionals to better understand the market and make informed decisions. The Dream House Price Predictor project is aimed at predicting the prices of residential properties based on various features such as location, size, number of bedrooms, and other amenities. The project uses a dataset of real estate transactions and employs machine learning algorithms to build a predictive model. The model is trained on the historical data and tested on a validation set to ensure its accuracy. The results of the project can be used by real estate agents, property buyers, and sellers to make informed decisions about pricing and investment opportunities. This project demonstrates the potential of machine learning to assist in the real estate market and provides a valuable tool for predicting property prices.

A novel hybrid model based on deep learning and error correction for crude oil futures prices forecast

Energy is a crucial basis for ensuring people's life quality and advancing social and economic development. Whereas, the crude oil futures prices are influenced by several factors such as energy policies, which shows strong non-linearity and high volatility. Accurately predicting price changes of crude oil futures is a challenging task. In this study, a new hybrid model, namely VILIG based on the "decomposition-prediction-ensemble-error correction" framework, is constructed to predict the closing prices of West Texas Intermediate (WTI) and Brent crude oil futures prices. First, variational modal decomposition (VMD) is applied to decompose the original price dataset into several sub-models. Then, each sub-model is used as an input to the Long-short term memory network (LSTM) and an improved golden jackal optimization (IGJO) algorithm is proposed to optimize the hyperparameters of the LSTM. Subsequently, an improved fully ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is introduced to perform a secondary decomposition of the error sequence and gate recurrent unit (GRU) is used to predict the decomposed error sequences separately. Finally, the prediction outcomes are obtained by linear aggregation. In addition, based on the point prediction results, this study presents kernel density estimation (KDE) for interval estimation to perform uncertainty prediction. The empirical results show that the VILIG model outperforms all the currently available major models in terms of quantitative evaluation metrics. The model can provide a data base for decision making for crude oil futures investors and market regulators.

Multi-step carbon price forecasting using a hybrid model based on multivariate decomposition strategy and deep learning algorithms

Accurate prediction of carbon price effectively ensures the stability of the carbon trading market and reduces carbon emissions. However, making accurate prediction is challenging because the carbon price is highly nonlinear and nonstationary due to complex influential factors. Thus, we propose a multifactorial hybrid forecasting framework, ET-MVMD-LSTM, to integrate three advanced algorithms for a reliable multi-step ahead prediction of the carbon price. First, extremely randomized tree (ET) is used to determine the optimal input variables for the modeling to follow. Then, multivariate variational mode decomposition (MVMD) is executed to simultaneously decompose the screened input variables into relatively regular sub-modes, which reflect characteristics at different scales. Subsequently, long short-term memory (LSTM) with a stable forecasting ability is employed to model each mode individually to effectively extract the long-term trend and short-term fluctuation features. The final forecast is reconstructed by the ensemble of the predictions of all sub-modes. Last, systematical studies on two European Union Emissions Trading Scheme carbon price datasets indicate that the proposed ET-MVMD-LSTM framework outperforms several advanced baseline models in terms of accuracy and stability, which prove the framework is deemed promising and practical for carbon price prediction.

RETRACTED: An Evolutionary Technique for Building Neural Network Models for Predicting Metal Prices

In this research, a neural network (NN) model for metal price forecasting based on an evolutionary approach is proposed. Both the neural network model’s network parameters and network architecture are selected automatically. The time series metal price data set is used to construct a novel fitness function that takes into account both error minimizations and the reproduction of the auto-correlation function. Calculating the average entropy values allowed the selection of the input parameter count for the neural network model. Gold price forecasting was performed using the proposed methodology. The optimal hidden node number, learning rate, and momentum are 9, 0.026, and 0.76, respectively, according to the evolutionary-based NN model. The proposed strategy is shown to reduce estimation error while also reproducing the auto-correlation function of the time series data set by the validation results with gold price data. The performance of the proposed method is better than other current methods, according to a comparison study.

State formation and market integration: Germany, 1780–1830

The rise of modern states is an important factor for economic development. We test the effects of territorial consolidation and the increase in legal capacity on market integration. The political transformation of Germany in the wake of the Napoleonic Wars, which reduced territorial fragmentation and transformed former semi-autonomous estates to sovereign polities, serves as a natural experiment. We apply a difference-in-differences framework to a new dataset of grain prices and show that territorial consolidation reduced trade costs conditional on trade reforms that replaced heterogenous internal duties by a unified system of external tariffs. The effect was equivalent to a reduction of price gaps by 31 percent. Cities that were part of Prussia both before and after the Wars and experienced trade reform saw a reduction in price gaps of similar magnitude. By contrast, there was no market integration in late-reformer states such as Hanover and Saxony. Trade reforms were the main channel through which territorial consolidation fostered market integration.