Search

• Introduce the state-of-art temporal fusion transformers (TFT) into economic system forecasting based on the high compatibility between deep learning and the nonlinear characteristics of socio-economic systems. • Propose a scientific economic system forecasting framework on the foundation of the extended gross final product (GFP). • Build a four-dimensional evaluation system including numerical error, direction accuracy, timing error and turning point accuracy. • Empirically forecast the monthly output indicators of the Chinese macroeconomic system. • TFT results have obvious advantages over benchmark models including ARIMA, BP, LSTM, TCN and N-BEATS through comparison analysis. Although helpful in reducing the uncertainty associated with economic activities, economic forecasting often suffers from low accuracy. Recognizing the high compatibility between deep learning and the nonlinear characteristics of socioeconomic systems, in this paper, we introduce state-of-the-art temporal fusion transformers (TFTs) into the field of economic system forecasting and predict the performance of the Chinese macroeconomic system. Based on an extended analysis of gross final product (GFP) and the intertemporal dynamic relationship between demand-side indicators and output indicators, we establish a scientific economic forecasting framework. To summarize the forecasting characteristics of the TFT algorithm, we compare its one-step and three-step modeling effects in forecasting output indicators with a series of representative benchmark models. According to our proposed four-dimensional evaluation system, the forecasts for China's macroeconomic system provided by the TFT model have obvious advantages in terms of overall stability, forecasting efficiency, reduction of numerical and timing errors, direction accuracy, and turning point accuracy. The forecast results show that China's economy faces a risk of slowing growth in the post-pandemic period. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a novel combination of the hidden Markov model (HMM) and the fuzzy models for forecasting stock market data. In a previous study we used an HMM to identify similar data patterns from the historical data and then used a weighted average to generate a ‘one-day-ahead’ forecast. This paper uses a similar approach to identify data patterns by using the HMM and then uses fuzzy logic to obtain a forecast value. The HMM''s log-likelihood for each of the input data vectors is used to partition the dataspace. Each of the divided dataspaces is then used to generate a fuzzy rule. The fuzzy model developed from this approach is tested on stock market data drawn from different sectors. Experimental results clearly show an improved forecasting accuracy compared to other forecasting models such as, ARIMA, artificial neural network (ANN) and another HMM-based forecasting model. [Copyright &y& Elsevier]

Abstract: The goal of this paper is to augment the ordinal temporal-difference type (TD-type) reinforcement learning model in order to detect the most suitable learning model of the human decision-making process in financial investment tasks. The simplicity and robustness of the TD-type learning model is fascinating. However, the available evidence and our observation suggest the necessity of introducing the nonlinear effect in learning and the possibility that additional factors might play important roles in the investment decision-making process. To extend the ordinal TD-type learning model, we adopt a three-layered perceptron as the basis function and the hierarchical Bayesian method to calibrate the parameter values. The result of the predictive test suggests that the augmented TD-type learning model constructed in this paper can evade the overfitting and can predict people''s investment behavior well as compared to other familiar learning models. [Copyright &y& Elsevier]

Forecasting stock price is a hot issue for stock investors, dealers and brokers. However, it is difficult to find out the best time point to buy or sell stock, since many variables will affect the stock market, and stock dataset is time series data. Therefore many time series models have been proposed for forecasting stock price; furthermore the previous time series methods still have some problems. Hence, this paper proposes a novel ANFIS (Adaptive Neuro Fuzzy Inference System) time series model based on integrated nonlinear feature selection (INFS) method for stock forecasting. Firstly, this study proposed an integrated nonlinear feature selection method to select the important technical indicators objectively. Secondly, it used ANFIS to build time series model and test forecast performance, then utilized adaptive expectation model to strengthen the forecasting performance. In order to evaluate the performance of proposed model, the TAIEX and HSI stock market transaction data from 1998 to 2006 are collected as experimental dataset and compared with other models. The results show that the proposed method outperforms the listing models in accuracy, profit evaluation and statistical test. [ABSTRACT FROM AUTHOR]

Forecasting exchange rates is an important financial problem. In this paper, an improved deep belief network (DBN) is proposed for forecasting exchange rates. By using continuous restricted Boltzmann machines (CRBMs) to construct a DBN, we update the classical DBN to model continuous data. The structure of DBN is optimally determined through experiments for application in exchange rates forecasting. Also, conjugate gradient method is applied to accelerate the learning for DBN. In the experiments, three exchange rate series are tested and six evaluation criteria are adopted to evaluate the performance of the proposed method. Comparison with typical forecasting methods such as feed forward neural network (FFNN) shows that the proposed method is applicable to the prediction of foreign exchange rate and works better than traditional methods. [ABSTRACT FROM AUTHOR]

Stock market forecasting is an important and challenging task. Conventional single objective optimization based adaptive prediction models reported in the literature do not satisfy many cost functions simultaneously. Very few reported materials are available on the development of multiobjective optimization based stock market prediction models. In this paper multiobjective particle swarm optimization (MOPSO) and nondominated sorting genetic algorithm version-II (NSGA-II) have been introduced to effectively train the adaptive stock market prediction models which simultaneously optimize four performance measures. The model developed is an adaptive one with nonlinearity introduced at the input end by Legendre polynomial expansion scheme. The stepwise algorithms are provided to develop the model and simulation study is carried to evaluate the performance. To arrive at the best possible solutions from these models, fuzzy logic based decision making strategy is suggested. Close examination of simulation results reveals that in terms of directional accuracy (DA) and computation time MOPSO based model is better where as in terms of average relative variance (ARV) and I-metric the NSGA-II model is superior. However, with regard to mean average percentage of error (MAPE) and Theli’s U, MOPSO is better above one month ahead prediction. But for below one month ahead prediction, the NSGA-II model is preferable. To facilitate comparison two single objective optimization based models (PSO and GA based) are also developed and the performance has been obtained through simulation study. Comparison of the results demonstrate that in terms of MAPE and DA the performance of multiobjective is better where as the single objective optimization model exhibit superior performance in terms of Theli’s U and the ARV. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we propose a new type of adaptive fuzzy inference system with a view to achieve improved performance for forecasting nonlinear time series data by dynamically adapting the fuzzy rules with arrival of new data. The structure of the fuzzy model utilized in the proposed system is developed based on the log-likelihood value of each data vector generated by a trained Hidden Markov Model. As part of its adaptation process, our system checks and computes the parameter values and generates new fuzzy rules as required, in response to new observations for obtaining better performance. In addition, it can also identify the most appropriate fuzzy rule in the system that covers the new data; and thus requires to adapt the parameters of the corresponding rule only, while keeping the rest of the model unchanged. This intelligent adaptive behavior enables our adaptive fuzzy inference system (FIS) to outperform standard FISs. We evaluate the performance of the proposed approach for forecasting stock price indices. The experimental results demonstrate that our approach can predict a number of stock indices, e.g., Dow Jones Industrial (DJI) index, NASDAQ index, Standard and Poor500 (S&P500) index and few other indices from UK (FTSE100), Germany (DAX) , Australia (AORD) and Japan (NIKKEI) stock markets, accurately compared with other existing computational and statistical methods. [Copyright &y& Elsevier]

Abstract: Financial time series forecasting has become a challenge because it is noisy, non-stationary and chaotic. Most of the existing forecasting models for this problem do not take market sentiment into consideration. To overcome this limitation, motivated by the fact that market sentiment contains some useful forecasting information, this paper uses textual information to aid the financial time series forecasting and presents a novel text mining approach via combining ARIMA and SVR (Support Vector Regression) to forecasting. The approach contains three steps: representing textual data as feature vectors, using ARIMA to analyze the linear part and developing a SVR model based only on textual feature vector to model the nonlinear part. To verify the effectiveness of the proposed approach, quarterly ROEs (Return of Equity) of six security companies are chosen as the forecasting targets. Comparing with some existing state-of-the-art models, the proposed approach gives superior results. It indicates that the proposed model that uses additional market sentiment provides a promising alternative to financial time series prediction. [Copyright &y& Elsevier]

Abstract: Stock market forecasting has long been a focus of financial time series prediction. In this paper, we investigate and forecast the price fluctuation by an improved Legendre neural network. In the predictive modeling, we assume that the investors decide their investing positions by analyzing the historical data on the stock market, so that the historical data can affect the volatility of the current stock market, and a random time strength function is introduced in the forecasting model to give a weight for each historical data. The impact strength of the historical data on the market is developed by a random process, where a tendency function and a random Brownian volatility function are applied to describe the behavior of the time strength, here Brownian motion makes the model have the effect of random movement while maintaining the original fluctuation. Further, the empirical research is made in testing the predictive effect of SAI, SBI, DJI and IXIC in the established model, and the corresponding statistical comparisons of the above market indexes are also exhibited. [Copyright &y& Elsevier]

Abstract: Nowadays a great deal of effort has been made in order to gain advantages in foreign exchange (FX) rates predictions. However, most existing techniques seldom excel the simple random walk model in practical applications. This paper describes a self-organising network formed on the basis of a mixture of adaptive autoregressive models. The proposed network, termed self-organising mixture autoregressive (SOMAR) model, can be used to describe and model nonstationary, nonlinear time series by means of a number of underlying local regressive models. An autocorrelation coefficient-based measure is proposed as the similarity measure for assigning input samples to the underlying local models. Experiments on both benchmark time series and several FX rates have been conducted. The results show that the proposed method consistently outperforms other local time series modelling techniques on a range of performance measures including the mean-square-error, correct trend predication percentage, accumulated profit and model variance. [Copyright &y& Elsevier]

Abstract: This paper compares the predictive performance of ARIMA, artificial neural network and the linear combination models for forecasting wheat price in Chinese market. Empirical results show that the combined model can improve the forecasting performance significantly in contrast with its counterparts in terms of the error evaluation measurements. However, as far as turning points and profit criterions are concerned, the ANN model is best as well as at capturing a significant number of turning points. The results are conflicting when implementing dissimilar forecasting criteria (the quantitative and the turning points measurements) to evaluate the performance of three models. The ANN model is overall the best model, and can be used as an alternative method to model Chinese future food grain price. [Copyright &y& Elsevier]