Search

Purpose: The purpose of the paper is to better measure the risks and volatility of the Bitcoin market by using the proposed novel risk measurement model. Design/methodology/approach: The joint regression analysis of value at risk (VaR) and expected shortfall (ES) can effectively overcome the non-elicitability problem of ES to better measure the risks and volatility of financial markets. And because of the incomparable advantages of the long- and short-term memory (LSTM) model in processing non-linear time series, the paper embeds LSTM into the joint regression combined forecasting framework of VaR and ES, constructs a joint regression combined forecasting model based on LSTM for jointly measuring VaR and ES, i.e. the LSTM-joint-combined (LSTM-J-C) model, and uses it to investigate the risks of the Bitcoin market. Findings: Empirical results show that the proposed LSTM-J-C model can improve forecasting performance of VaR and ES in the Bitcoin market more effectively compared with the historical simulation, the GARCH model and the joint regression combined forecasting model. Social implications: The proposed LSTM-J-C model can provide theoretical support and practical guidance to cryptocurrency market investors, policy makers and regulatory agencies for measuring and controlling cryptocurrency market risks. Originality/value: A novel risk measurement model, namely LSTM-J-C model, is proposed to jointly estimate VaR and ES of Bitcoin. On the other hand, the proposed LSTM-J-C model provides risk managers more accurate forecasts of volatility in the Bitcoin market. [ABSTRACT FROM AUTHOR]

Intelligent education systems have enabled personalized learning (PL). In PL, students are presented with educational contents that are consistent with their personal knowledge states (KS), and the critical task is accurately estimating these states through data. Knowledge tracing (KT) infers KS (latent) through historical student interactions (observed) with the knowledge components (KCs). A wide variety of KT techniques have been developed, from Bayesian Knowledge Tracing (BKT) to Deep Knowledge Tracing (DKT). However, in most of these methods, the KCs are represented as stand-alone entities, and the effect of representing KCs using contexts such as learning-related factors has been under-investigated. Also, KT needs to generate personalized results to facilitate tasks such as exercise recommendation. In this paper, we propose two approaches that use a contextualized representation of KCs, one with a content-based approach and another with a Long Short Term Memory (LSTM) network plus a personalization mechanism. By performing extensive experiments on two real-world datasets, results show not only a tangible improvement in prediction accuracy in the KT task compared to existing methods, but also its effectiveness in improving the recommendation precision. [ABSTRACT FROM AUTHOR]

Fault prediction technology provides a way to reduce the loss caused by equipment failure. Currently, many efforts of failure prediction pay more attention to the fault trend and the remaining useful life. This paper devotes to predicting a specific failure mode of device in the future. We propose a two-step prediction method with two sub-models to predict the fault mode. The first model, named regression model, combines Attention-based-LSTM (Long Short-Term Memory) and Random Forest (RF) to predict time series trends, where wavelet packet analysis is adopted to extract elementary features of time series and form multivariable time series. Based on the status data forecasted by the first model, the second model, named classification model, combines Attention-based-LSTM and Extra-Tree (ET) to classify fault mode. The classified fault will occur in the device at some point in the future. In the regression model, Attention-based-LSTM performs deep level feature extraction of vibration sensor signals, and the result is fed to the last layer (i.e., an RF layer), which takes responsibility for predicting the future sequence. The future sequence is then provided to the classification model, where Attention-based-LSTM is used to extract implicit features, and ET classifier is used to accept these features and figure out the failure phenomenon. Our approach for predicting failure modes includes the severity and type of fault, which are rarely investigated synthetically. The experimental results of bearing data show that the sub-models can achieve high prediction accuracy and our method can predict the future failure mode with precision. [ABSTRACT FROM AUTHOR]

• A predicting model for the long-term epidemic trend of COVID-19 by using LSTM with rolling update mechanism is proposed. • The 150-days ahead epidemic trend of COVID-19 in Russia, Peru and Iran are estimated by our proposed model. • The results provide that the epidemic of Peru will end in early December. • The number of daily cases in Russia and Iran is expected to fall below 2000 and 1000 by mid-November and early December. • By introducing diffusion index, the effectiveness of preventive measures taken by the government are analyzed. The COVID-19 outbreak in late December 2019 is still spreading rapidly in many countries and regions around the world. It is thus urgent to predict the development and spread of the epidemic. In this paper, we have developed a forecasting model of COVID-19 by using a deep learning method with rolling update mechanism based on the epidemical data provided by Johns Hopkins University. First, as traditional epidemical models use the accumulative confirmed cases for training, it can only predict a rising trend of the epidemic and cannot predict when the epidemic will decline or end, an improved model is built based on long short-term memory (LSTM) with daily confirmed cases training set. Second, considering the existing forecasting model based on LSTM can only predict the epidemic trend within the next 30 days accurately, the rolling update mechanism is embedded with LSTM for long-term projections. Third, by introducing Diffusion Index (DI), the effectiveness of preventive measures like social isolation and lockdown on the spread of COVID-19 is analyzed in our novel research. The trends of the epidemic in 150 days ahead are modeled for Russia, Peru and Iran, three countries on different continents. Under our estimation, the current epidemic in Peru is predicted to continue until November 2020. The number of positive cases per day in Iran is expected to fall below 1000 by mid-November, with a gradual downward trend expected after several smaller peaks from July to September, while there will still be more than 2000 increase by early December in Russia. Moreover, our study highlights the importance of preventive measures which have been taken by the government, which shows that the strict controlment can significantly reduce the spread of COVID-19. [ABSTRACT FROM AUTHOR]

In this paper, Deep Learning-based models are used for predicting the number of novel coronavirus (COVID-19) positive reported cases for 32 states and union territories of India. Recurrent neural network (RNN) based long-short term memory (LSTM) variants such as Deep LSTM, Convolutional LSTM and Bi-directional LSTM are applied on Indian dataset to predict the number of positive cases. LSTM model with minimum error is chosen for predicting daily and weekly cases. It is observed that the proposed method yields high accuracy for short term prediction with error less than 3% for daily predictions and less than 8% for weekly predictions. Indian states are categorised into different zones based on the spread of positive cases and daily growth rate for easy identification of novel coronavirus hot-spots. Preventive measures to reduce the spread in respective zones are also suggested. A website is created where the state-wise predictions are updated using the proposed model for authorities,researchers and planners. This study can be applied by other countries for predicting COVID-19 cases at the state or national level. [ABSTRACT FROM AUTHOR]