Deep Learning for Financial Time Series Prediction:A State-of-the-Art Review of Standalone and HybridModels

Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.

RL and AHP-Based Multi-Timescale Multi-Clock Source Time Synchronization for Distribution Power Internet of Things

Time synchronization(TS)is crucial for ensuring the secure and reliable functioning of the distribution power Internet of Things(IoT).Multi-clock source time synchronization(MTS)has significant advantages of high reliability and accuracy but still faces challenges such as optimization of the multi-clock source selection and the clock source weight calculation at different timescales,and the coupling of synchronization latency jitter and pulse phase difference.In this paper,the multi-timescale MTS model is conducted,and the reinforcement learning(RL)and analytic hierarchy process(AHP)-based multi-timescale MTS algorithm is designed to improve the weighted summation of synchronization latency jitter standard deviation and average pulse phase difference.Specifically,the multi-clock source selection is optimized based on Softmax in the large timescale,and the clock source weight calculation is optimized based on lower confidence bound-assisted AHP in the small timescale.Simulation shows that the proposed algorithm can effectively reduce time synchronization delay standard deviation and average pulse phase difference.

高被引还是零被引:基于论文被引的最佳科研合作规模研究--来自Financial Times TOP 45商学院期刊的证据

近年来,科研论文的合著现象及其与论文影响力之间的关系受到广泛关注。本文以1997—2013年Financial Times TOP 45商学院国际期刊论文为研究对象,对作者数量与论文被引(高被引还是零被引)之间的关系进行实证研究,从论文影响力方面揭示商学领域是否存在最佳科研合作规模。研究发现:①与单独作者相比,多作者合作对论文总被引频次具有显著的正向影响,而且多作者合作论文成为高被引的概率更高,而成为零被引的概率更低;②作者数量与论文总被引频次之间存在显著的倒U形关系;进一步研究发现,作者数量与高被引论文概率呈倒U形关系,而与零被引论文概率呈正U形关系,且转折点均约为3人,表明商学领域存在使论文成为高被引而避免成为零被引的最佳合作规模;③分时间阶段实证结果表明,基于高被引和零被引的论文最佳合作规模逐步由2~3人增加至3~4人。

Minister Shi Dazhen Answers the Reporters' (of Britain "Financial Times") Questions

On June 3 1996, Minister of Electric Power Shi Dazhen accepted news-covering of Britain "Financial Times" resident reporter in Beijing Tony Walker, resident reporter in Hong Kong John Ridding and Asian Editor Peter Montagnon, and answered their questions in the aspects of the 9th Five-year Development Planning of China’s Electric Power and some related issues.

Hurst Exponent Analysis of Financial Time Series

Statistical properties of stock market time series and the implication of their Hurst exponents are discussed. Hurst exponents of DJIA (Dow Jones Industrial Average) components are tested using re scaled range analysis. In addition to the original stock return series, the linear prediction errors of the daily returns are also tested. Numerical results show that the Hurst exponent analysis can provide some information about the statistical properties of the financial time series.

Reliability Analysis of Correlated Competitive and Dependent Components Considering Random Isolation Times

In the Internet of Things(IoT)system,relay communication is widely used to solve the problem of energy loss in long-distance transmission and improve transmission efficiency.In Body Sensor Network(BSN)systems,biosensors communicate with receiving devices through relay nodes to improve their limited energy efficiency.When the relay node fails,the biosensor can communicate directly with the receiving device by releasing more transmitting power.However,if the remaining battery power of the biosensor is insufficient to enable it to communicate directly with the receiving device,the biosensor will be isolated by the system.Therefore,a new combinatorial analysis method is proposed to analyze the influence of random isolation time(RIT)on system reliability,and the competition relationship between biosensor isolation and propagation failure is considered.This approach inherits the advantages of common combinatorial algorithms and provides a new approach to effectively address the impact of RIT on system reliability in IoT systems,which are affected by competing failures.Finally,the method is applied to the BSN system,and the effect of RIT on the system reliability is analyzed in detail.

Internet of Things Enabled Energy Aware Metaheuristic Clustering for Real Time Disaster Management

Wireless Sensor Networks(WSNs)are a major element of Internet of Things(IoT)networks which offer seamless sensing and wireless connectivity.Disaster management in smart cities can be considered as a safety critical application.Therefore,it becomes essential in ensuring network accessibility by improving the lifetime of IoT assisted WSN.Clustering and multihop routing are considered beneficial solutions to accomplish energy efficiency in IoT networks.This article designs an IoT enabled energy aware metaheuristic clustering with routing protocol for real time disaster management(EAMCR-RTDM).The proposed EAMCR-RTDM technique mainly intends to manage the energy utilization of nodes with the consideration of the features of the disaster region.To achieve this,EAMCR-RTDM technique primarily designs a yellow saddle goatfish based clustering(YSGF-C)technique to elect cluster heads(CHs)and organize clusters.In addition,enhanced cockroach swarm optimization(ECSO)based multihop routing(ECSO-MHR)approach was derived for optimal route selection.The YSGF-C and ECSO-MHR techniques compute fitness functions using different input variables for achieving improved energy efficiency and network lifetime.The design of YSGF-C and ECSO-MHR techniques for disaster management in IoT networks shows the novelty of the work.For examining the improved outcomes of the EAMCR-RTDM system,a wide range of simulations were performed and the extensive results are assessed in terms of different measures.The comparative outcomes highlighted the enhanced outcomes of the EAMCRRTDM algorithm over the existing approaches.

Performance evaluation of series and parallel strategies for financial time series forecasting

Background:Improving financial time series forecasting is one of the most challenging and vital issues facing numerous financial analysts and decision makers.Given its direct impact on related decisions,various attempts have been made to achieve more accurate and reliable forecasting results,of which the combining of individual models remains a widely applied approach.In general,individual models are combined under two main strategies:series and parallel.While it has been proven that these strategies can improve overall forecasting accuracy,the literature on time series forecasting remains vague on the choice of an appropriate strategy to generate a more accurate hybrid model.Methods:Therefore,this study’s key aim is to evaluate the performance of series and parallel strategies to determine a more accurate one.Results:Accordingly,the predictive capabilities of five hybrid models are constructed on the basis of series and parallel strategies compared with each other and with their base models to forecast stock price.To do so,autoregressive integrated moving average(ARIMA)and multilayer perceptrons(MLPs)are used to construct two series hybrid models,ARIMA-MLP and MLP-ARIMA,and three parallel hybrid models,simple average,linear regression,and genetic algorithm models.Conclusion:The empirical forecasting results for two benchmark datasets,that is,the closing of the Shenzhen Integrated Index(SZII)and that of Standard and Poor’s 500(S&P 500),indicate that although all hybrid models perform better than at least one of their individual components,the series combination strategy produces more accurate hybrid models for financial time series forecasting.

Modelling and Analysis on Noisy Financial Time Series

Building the prediction model(s) from the historical time series has attracted many researchers in last few decades. For example, the traders of hedge funds and experts in agriculture are demanding the precise models to make the prediction of the possible trends and cycles. Even though many statistical or machine learning (ML) models have been proposed, however, there are no universal solutions available to resolve such particular problem. In this paper, the powerful forward-backward non-linear filter and wavelet-based denoising method are introduced to remove the high level of noise embedded in financial time series. With the filtered time series, the statistical model known as autoregression is utilized to model the historical times aeries and make the prediction. The proposed models and approaches have been evaluated using the sample time series, and the experimental results have proved that the proposed approaches are able to make the precise prediction very efficiently and effectively.

Age-Driven Joint Sampling and Non-Slot Based Scheduling for Industrial Internet of Things

Effective control of time-sensitive industrial applications depends on the real-time transmission of data from underlying sensors.Quantifying the data freshness through age of information(AoI),in this paper,we jointly design sampling and non-slot based scheduling policies to minimize the maximum time-average age of information(MAoI)among sensors with the constraints of average energy cost and finite queue stability.To overcome the intractability involving high couplings of such a complex stochastic process,we first focus on the single-sensor time-average AoI optimization problem and convert the constrained Markov decision process(CMDP)into an unconstrained Markov decision process(MDP)by the Lagrangian method.With the infinite-time average energy and AoI expression expended as the Bellman equation,the singlesensor time-average AoI optimization problem can be approached through the steady-state distribution probability.Further,we propose a low-complexity sub-optimal sampling and semi-distributed scheduling scheme for the multi-sensor scenario.The simulation results show that the proposed scheme reduces the MAoI significantly while achieving a balance between the sampling rate and service rate for multiple sensors.

Short-Term Financial Time Series Forecasting Integrating Principal Component Analysis and Independent Component Analysis with Support Vector Regression

Financial time series forecasting could be beneficial for individual as well as institutional investors. But, the high noise and complexity residing in the financial data make this job extremely challenging. Over the years, many researchers have used support vector regression (SVR) quite successfully to conquer this challenge. In this paper, an SVR based forecasting model is proposed which first uses the principal component analysis (PCA) to extract the low-dimensional and efficient feature information, and then uses the independent component analysis (ICA) to preprocess the extracted features to nullify the influence of noise in the features. Experiments were carried out based on 16 years’ historical data of three prominent stocks from three different sectors listed in Dhaka Stock Exchange (DSE), Bangladesh. The predictions were made for 1 to 4 days in advance targeting the short term prediction. For comparison, the integration of PCA with SVR (PCA-SVR), ICA with SVR (ICA-SVR) and single SVR approaches were applied to evaluate the prediction accuracy of the proposed approach. Experimental results show that the proposed model (PCA-ICA-SVR) outperforms the PCA-SVR, ICA-SVR and single SVR methods.

A Mixture Model Parameters Estimation Algorithm for Inter-Contact Times in Internet of Vehicles

Communication opportunities among vehicles are important for data transmission over the Internet of Vehicles(IoV).Mixture models are appropriate to describe complex spatial-temporal data.By calculating the expectation of hidden variables in vehicle communication,Expectation Maximization(EM)algorithm solves the maximum likelihood estimation of parameters,and then obtains the mixture model of vehicle communication opportunities.However,the EM algorithm requires multiple iterations and each iteration needs to process all the data.Thus its computational complexity is high.A parameter estimation algorithm with low computational complexity based on Bin Count(BC)and Differential Evolution(DE)(PEBCDE)is proposed.It overcomes the disadvantages of the EM algorithm in solving mixture models for big data.In order to reduce the computational complexity of the mixture models in the IoV,massive data are divided into relatively few time intervals and then counted.According to these few counted values,the parameters of the mixture model are obtained by using DE algorithm.Through modeling and analysis of simulation data and instance data,the PEBCDE algorithm is verified and discussed from two aspects,i.e.,accuracy and efficiency.The numerical solution of the probability distribution parameters is obtained,which further provides a more detailed statistical model for the distribution of the opportunity interval of the IoV.

Methodological Approaches to Study Internet Financial Communication

The aim of this paper is to show how qualitative and quantitative approaches can be complementary to study internet financial communication in a thesis by papers and how grounded theory （GT） can be the link among the different papers of the thesis. The study context of our thesis was the unregulated markets of New York Stock Exchange （NYSE） Euronext Brussels and the problematic rose from this context： What is the voluntary effort of communication when there is no obligation of internet financial communication？ Four papers tried to answer this central question and other following research questions. To answer those research questions, several methodological approaches were used： content analysis of websites and scoring, linear regression, paired sample, and interviews. At the end of our thesis by papers, we discovered that GT was the general methodological travel among the papers： Every article had for vocation to try to answer the questions raised by the previous article.

Internet Usage and Household Investment on Risky Financial Assets

Using panel data from the China Family Panel Studies for 2010,2014 and 2016,this paper uses a two-part model,with the first part using a fixed-effects panel logit model and the second part using a linear logit fixed-effects model to study the impact of Internet usage on Chinese households’participation in risky financial markets and the intensity of investment in risky assets after participation.The results find that Internet usage can promote household participation in the risky finance market and increase household investment in risky assets.Therefore,accelerating Internet usage can promote Chinese households’participation in the risk finance market.

The Financial Impact of the Internet on the Analysis of Commercial Banking

As we all know, the development of Internet-based financial model of commercial banks have impacted the traditional banking business, but this much impact in the end, whether commercial banks caused a fatal impact, this article will focus on the analysis.

Research on the Reasonable Strategy of the Development of Commercial Banks under the Perspective of P2P Internet Financial Risks

In this paper, we conduct research on the reasonable strategy of the development of commercial banks under the perspective of P2P Internet financial risks. P2P financial model mainly for China＇ s small and medium enterprises and individuals to provides financing services. Generally need to use e-commerce professional network platform lending to help both sides to establish lending relationship and complete the related formalities. Traditional commercial banks need reform to keep up with the novel financial tools related to the Internet financing which will be discussed below.

Analysis on the financing strategies of small and medium sized clothing enterprises under the Internet financial model

Small and medium sized clothing enterprises have become an important force to promote China＇s economic transformation. But the shortage of funds in the development of small and medium sized clothing enterprises is still a major problem. The development of Intemet financial model is of great significance to the small and Medium Sized Clothing Enterprises .It is helpful to solve the problems of information asymmetry, credit rationing and high loan cost in the financing of small and medium sized clothing enterprises..In many financial models on the interne＇., to our vast number of small and medium-sized enterprises provide convenient services, but in the face of this model using diffcrent opinions, and there is no pertinence, for most of the enterprises are usually similar situation was a summary and recommendations, there are a handful of targeted research ,This research is for research, in order to solve the financing problems of China＇s small and medium-sized garment enterprises countermeasures were studied to find a suitable China＇s small and medium-sized garment enterprises financing path with, for small and medium-sized garment enterprises in the capital needs of the guiding role, for the enterprise to avoid financial risk. the lnternet financial model to solve the financing problem of small and medium-sized garment enterprises play the important role, we should expand Internet banking, so that more small and medium-sized garment enterprises get better development.

Research on the Influencing Factors of Purchasing Internet Financial Wealth Management Products Based on AHP

Internet financial wealth management product(IFWMP)has recently been one of the most gained popularity.There are limited quantitative research on IFWMP which can help customers to choose products based on the significance of each factor.In this paper,a multi-criteria decision-making model for IFWMP was developed,namely the analytic hierarchy process(AHP)which is commonly used to make decisions for unstructured problems through quantifying weights of each criterion.This paper investigated ten influential factors relevant to the purchase of IFWMP and analyzed the frequency of collected response to show the significance of the factors.Based on the quantified weights,the results of the research indicated that compatibility,product liquidity,perceived ease of use,and perceived usefulness affected investors purchasing behaviors and that every investor should pay great attention to.

Research on the Influencing Factors of Purchasing Internet Financial Wealth Management Products based on AHP

Internet financial wealth management product(IFWMP)has recently been one of the most popularity.There is limited quantitative research on IFWMP which can helps customers to choose the products based on the significance of each factor.In the paper,a multi-criteria decision-making model of IFWMP was developed,namely analytic hierarchy process(AHP)which is used to make decisions to the unstructured problems through quantifying weights of each criterion.This paper investigated ten influential factors relevant to the purchase of IFWMP and analyzed the frequency of collected responds to show the significance of factors.Based on the quantified weights,the result of the research indicated that compatibility,product liquidity,perceived ease of use and perceived usefulness affect the investors purchasing behaviors most that every investors should pay great attention to.

The finite-time ruin probability in the presence of Sarmanov dependent financial and insurance risks

Consider a discrete-time insurance risk model. Within period i, i≥ 1, Xi and Yi denote the net insurance loss and the stochastic discount factor of an insurer, respectively. Assume that {（Xi, Yi）, i≥1） form a sequence of independent and identically distributed random vectors following a common bivariate Sarmanov distribution. In the presence of heavy-tailed net insurance losses, an asymptotic formula is derived for the finite-time ruin probability.