Search results

Because the dynamic characteristics of the stock market are nonlinear, it is unclear whether stock prices can be predicted. This paper aims to explore the predictability of the stock price index from a long-memory perspective. The authors propose hybrid models to predict the next-day closing price index and explore the policy effects behind stock prices. The paper aims to discuss the aforementioned ideas.

The authors found a long memory in the stock price index series using modified R/S and GPH tests, and propose an improved bi-directional gated recurrent units (BiGRU) hybrid network framework to predict the next-day stock price index. The proposed framework integrates (1) A de-noising module—Singular Spectrum Analysis (SSA) algorithm, (2) a predictive module—BiGRU model, and (3) an optimization module—Grid Search Cross-validation (GSCV) algorithm.

Three critical findings are long memory, fit effectiveness and model optimization. There is long memory (predictability) in the stock price index series. The proposed framework yields predictions of optimum fit. Data de-noising and parameter optimization can improve the model fit.

The empirical data are obtained from the financial data of listed companies in the Wind Financial Terminal. The model can accurately predict stock price index series, guide investors to make reasonable investment decisions, and provide a basis for establishing individual industry stock investment strategies.

If the index series in the stock market exhibits long-memory characteristics, the policy implication is that fractal markets, even in the nonlinear case, allow for a corresponding distribution pattern in the value of portfolio assets. The risk of stock price volatility in various sectors has expanded due to the effects of the COVID-19 pandemic and the R-U conflict on the stock market. Predicting future trends by forecasting stock prices is critical for minimizing financial risk. The ability to mitigate the epidemic’s impact and stop losses promptly is relevant to market regulators, companies and other relevant stakeholders.

Although long memory exists, the stock price index series can be predicted. However, price fluctuations are unstable and chaotic, and traditional mathematical and statistical methods cannot provide precise predictions. The network framework proposed in this paper has robust horizontal connections between units, strong memory capability and stronger generalization ability than traditional network structures. The authors demonstrate significant performance improvements of SSA-BiGRU-GSCV over comparison models on Chinese stocks.

In this “Info-plosion” era, recommendation systems (or recommenders) play a significant role in finding interesting items in the surge of online digital activity and e-commerce. The purpose of this paper is to model users' preference evolution to recommend potential items which users may be interested in.

A novel recommendation system, namely evolution-learning recommendation (ELR), is developed to precisely predict user interest for making recommendations. Differing from prior related methods, the authors integrate the matrix factorization (MF) and recurrent neural network (RNN) to effectively describe the variation of user preferences over time.

A novel cumulative factorization technique is proposed to efficiently decompose a rating matrix for discovering latent user preferences. Compared to traditional MF-based methods, the cumulative MF could reduce the utilization of computation resources. Furthermore, the authors depict the significance of long- and short-term effects in the memory cell of RNN for evolution patterns. With the context awareness, a learning model, V-LSTM, is developed to dynamically capture the evolution pattern of user interests. By using a well-trained learning model, the authors predict future user preferences and recommend related items.

Based on the relations among users and items for recommendation, the authors introduce a novel concept, virtual communication, to effectively learn and estimate the correlation among users and items. By incorporating the discovered latent features of users and items in an evolved manner, the proposed ELR model could promote “right” things to “right” users at the “right” time. In addition, several extensive experiments are performed on real datasets and are discussed. Empirical results show that ELR significantly outperforms the prior recommendation models. The proposed ELR exhibits great generalization and robustness in real datasets, including e-commerce, industrial retail and streaming service, with all discussed metrics.

Tourism spot or point-of-interest (POI) recommendation has become a common service in people's daily life. The purpose of this paper is to model users' check-in history in order to predict a set of locations that a user may soon visit.

The authors proposed a novel learning-based method, the pattern-based dual learning POI recommendation system as a solution to consider users' interests and the uniformity of popular POI patterns when making recommendations. Differing from traditional long short-term memory (LSTM), a new users’ regularity–POIs’ popularity patterns long short-term memory (UP-LSTM) model was developed to concurrently combine the behaviors of a specific user and common users.

The authors introduced the concept of dual learning for POI recommendation. Several performance evaluations were conducted on real-life mobility data sets to demonstrate the effectiveness and practicability of POI recommendations. The metrics such as hit rate, precision, recall and F-measure were used to measure the capability of ranking and precise prediction of the proposed model over all baselines. The experimental results indicated that the proposed UP-LSTM model consistently outperformed the state-of-the-art models in all metrics by a large margin.

This study contributes to the existing literature by incorporating a novel pattern–based technique to analyze how the popularity of POIs affects the next move of a particular user. Also, the authors have proposed an effective fusing scheme to boost the prediction performance in the proposed UP-LSTM model. The experimental results and discussions indicate that the combination of the user's regularity and the POIs’ popularity patterns in PDLRec could significantly enhance the performance of POI recommendation.

The deep learning-based recommender framework (DLRF) is based on an improved long short-term memory (LSTM) structure with additional controllers; thus, it considers contextual information for state transition. It also handles irregularities in the data to enhance performance in generating recommendations while modelling short-term preferences. An algorithm named a multi-preference integrated algorithm (MPIA) is proposed to have dynamic integration of both kinds of user preferences aforementioned. Extensive experiments are made using Amazon benchmark datasets, and the results are compared with many existing recommender systems (RSs).

RSs produce quality information filtering to the users based on their preferences. In the contemporary era, online RSs-based collaborative filtering (CF) techniques are widely used to model long-term preferences of users. With deep learning models, such as recurrent neural networks (RNNs), it became viable to model short-term preferences of users. In the existing RSs, there is a lack of dynamic integration of both long- and short-term preferences. In this paper, the authors proposed a DLRF for improving the state of the art in modelling short-term preferences and generating recommendations as well.

The results of the empirical study revealed that the MPIA outperforms existing algorithms in terms of performance measured using metrics such as area under the curve (AUC) and F1-score. The percentage of improvement in terms AUC is observed as 1.3, 2.8, 3 and 1.9% and in terms of F-1 score 0.98, 2.91, 2 and 2.01% on the datasets.

The algorithm uses attention-based approaches to integrate the preferences by incorporating contextual information.

According to the problem of crude oil price forecasting, the purpose of this paper is to propose a multi-step prediction method based on the empirical mode decomposition, long short-term memory network and GM (1,1) model.

First, the empirical mode decomposition method is used to decompose the crude oil price series into several components with different frequencies. Then, each subsequence is classified and synthesized based on the specific periodicity and other properties to obtain several components with different significant characteristics. Finally, all components are substituted into a suitable prediction model for fitting. LSTM models with different parameters are constructed for predicting specific components, which approximately and respectively represent short-term market disturbance and long-term influences. Rolling GM (1,1) model is constructed to simulate a series representing the development trend of oil price. Eventually, all results obtained from forecasting models are summarized to evaluate the performance of the model.

The model is respectively applied to simulate daily, weekly and monthly WTI crude oil price sequences. The results show that the model has high accuracy on the prediction, especially in terms of series representing long-term influences with lower frequency. GM (1,1) model has excellent performance on fitting the trend of crude oil price.

This paper combines GM (1,1) model with LSTM network to forecast WTI crude oil price series. According to the different characteristics of different sequences, suitable forecasting models are constructed to simulate the components.

The aim of this study is to evaluate of the predictive ability of goodwill and other intangible assets on forecasting corporate profitability. Subsequently, this study compares the efficiency of deep learning model to that of other machine learning models such as random forest (RF) and support vector machine (SVM) as well as traditional statistical methods such as the linear regression model.

Studies confirm that goodwill and intangibles are valuable assets that give companies a competitive advantage to increase profitability and shareholders’ returns. Thus, by using as sample Greek-listed financial data, this study investigates whether or not the inclusion of goodwill and intangible assets as input variables in this modified deep learning models contribute to the corporate profitability prediction accuracy. Subsequently, this study compares the modified long-short-term model with other machine learning models such as SVMs and RF as well as the traditional panel regression model.

The findings of this paper confirm that goodwill and intangible assets clearly improve the performance of a deep learning corporate profitability prediction model. Furthermore, this study provides evidence that the modified long short-term memory model outperforms other machine learning models such as SVMs and RF , as well as traditional statistical panel regression model, in predicting corporate profitability.

Limitation of this study includes the relatively small amount of data available. Furthermore, the aim is to challenge the authors’ modified long short-term memory by using listed corporate data of Greece, a code-law country that suffered severely during the recent fiscal crisis. However, this study proposes that future research may apply deep learning corporate profitability models on a bigger pool of data such as STOXX Europe 600 companies.

Subsequently, the authors believe that their paper is of interest to different professional groups, such as financial analysts and banks, which the authors’ paper can support in their corporate profitability evaluation procedure. Furthermore, as well as shareholders are concerned, this paper could be of benefit in forecasting management’s potential to create future returns. Finally, management may incorporate this model in the evaluation process of potential acquisitions of other companies.

The contributions of this work can be summarized in the following aspects. This study provides evidence that by including goodwill and other intangible assets in the authors’ input portfolio, prediction errors represented by root mean squared error are reduced. A modified long short-term memory model is proposed to predict the numerical value of the profitability (or the profitability ratio) in contrast to other studies which deal with trend predictions, i.e. the binomial output result of positive or negative earnings. Finally, posing an extra challenge to the authors’ deep learning model, the authors’ used financial statements according to International Financial Reporting Standard data of listed companies in Greece, a code-law country that suffered during the recent fiscal debt crisis, heavily influenced by tax legislation and characterized by its lower investors’ protection compared to common-law countries.

This paper aims to test the hedging ability of housing investment against inflation in Japan and the USA during the period 2000–2020.

This study applies the deep learning method and The exponential general autoregressive conditional heteroskedasticity in mean (1, 1) model with breaks.

Within the asymmetric framework, it is found that housing returns (HR) can hedge against inflation in both these markets, which mentions that when investing in the housing market in Japan and the USA, investors are compensated for bearing from inflation. This result is consistent with Fisher’s hypothesis. Especially, the empirical results show that the risk-return tradeoff is available in Japan’s housing market and not available in the US housing market. Any signal of a high inflation rate – referred to as “bad news” – may cause a drop in HR in Japan and a raise in the USA.

To the best of the author’s knowledge, this is one of the first studies using the deep learning method (long short-term memory model) to estimate the expected/unexpected inflation rates.

An intelligent personal assistant for personal computers (PCs) is a vital application for the current generation. The current computer personal assistant services checking frameworks are not proficient at removing significant data from PCs and long-range informal communication information.

The proposed verbalizers use long short-term memory to classify the user task and give proper guidelines to the users. The outcomes show that the proposed method determinedly handles heterogeneous information and improves precision. The main advantage of long short-term memory is that handle the long-term dependencies in the input data.

The proposed model gives the 22% mean absolute error. The proposed method reduces mean square error than support vector machine (SVM), convolutional neural network (CNN), multilayer perceptron (MLP) and K-nearest neighbors (KNN).

This paper fulfills the necessity of intelligent personal assistant for PCs using verbalizer.

The prediction of by-product gas is an important guarantee for the full utilization of resources. The purpose of this research is to predict gas consumption to provide a basis for gas dispatch and reduce the production cost of enterprises.

In this paper, a new method using the ensemble empirical mode decomposition (EEMD) and the back propagation neural network is proposed. Unfortunately, this method does not achieve the ideal prediction. Further, using the advantages of long short-term memory (LSTM) neural network for long-term dependence, a prediction method based on EEMD and LSTM is proposed. In this model, the gas consumption series is decomposed into several intrinsic mode functions and a residual term (r(t)) by EEMD. Second, each component is predicted by LSTM. The predicted values of all components are added together to get the final prediction result.

The results show that the root mean square error is reduced to 0.35%, the average absolute error is reduced to 1.852 and the R-squared is reached to 0.963.

A new gas consumption prediction method is proposed in this paper. The production data collected in the actual production process is non-linear, unstable and contains a lot of noise. But the EEMD method has the unique superiority in the analysis data aspect and may solve these questions well. The prediction of gas consumption is the result of long-term training and needs a lot of prior knowledge. Relying on LSTM can solve the problem of long-term dependence.

This paper aims to propose an improved version of portfolio optimization model through the prediction of the future behavior of stock returns using a combined wavelet-based long short-term memory (LSTM).

First, data are gathered and divided into two parts, namely, “past data” and “real data.” In the second stage, the wavelet transform is proposed to decompose the stock closing price time series into a set of coefficients. The derived coefficients are taken as an input to the LSTM model to predict the stock closing price time series and the “future data” is created. In the third stage, the mean-variance portfolio optimization problem (MVPOP) has iteratively been run using the “past,” “future” and “real” data sets. The epsilon-constraint method is adapted to generate the Pareto front for all three runes of MVPOP.

The real daily stock closing price time series of six stocks from the FTSE 100 between January 1, 2000, and December 30, 2020, is used to check the applicability and efficacy of the proposed approach. The comparisons of “future,” “past” and “real” Pareto fronts showed that the “future” Pareto front is closer to the “real” Pareto front. This demonstrates the efficacy and applicability of proposed approach.

Most of the classic Markowitz-based portfolio optimization models used past information to estimate the associated parameters of the stocks. This study revealed that the prediction of the future behavior of stock returns using a combined wavelet-based LSTM improved the performance of the portfolio.