Graph Co-Attentive Session-based Recommendation

Session-based recommendation aims to generate recommendations merely based on the ongoing session, which is a challenging task. Previous methods mainly focus on modeling the sequential signals or the transition relations between items in the current session using RNNs or GNNs to identify user’s intent for recommendation. Such models generally ignore the dynamic connections between the local and global item transition patterns, although the global information is taken into consideration by exploiting the global-level pair-wise item transitions. Moreover, existing methods that mainly adopt the cross-entropy loss with softmax generally face a serious over-fitting problem, harming the recommendation accuracy. Thus, in this article, we propose a Graph Co-Attentive Recommendation Machine (GCARM) for session-based recommendation. In detail, we first design a Graph Co-Attention Network (GCAT) to consider the dynamic correlations between the local and global neighbors of each node during the information propagation. Then, the item-level dynamic connections between the output of the local and global graphs are modeled to generate the final item representations. After that, we produce the prediction scores and design a Max Cross-Entropy (MCE) loss to prevent over-fitting. Extensive experiments are conducted on three benchmark datasets, i.e., Diginetica, Gowalla, and Yoochoose. The experimental results show that GCARM can achieve the state-of-the-art performance in terms of Recall and MRR, especially on boosting the ranking of the target item.

The COVID-19 Outbreak and Risk–Return Spillovers between Main and SME Stock Markets in the MENA Region

This study investigates return and asymmetric volatility spillovers and dynamic correlations between the main and small and medium-sized enterprise (SME) stock markets in Saudi Arabia and Egypt for the periods before and during the COVID-19 pandemic. Return and volatility spillovers are modelled using a VAR-asymmetric BEKK–GARCH (1,1) model, while a VAR-asymmetric DCC–GARCH (1,1) model is employed to model the dynamic conditional correlations between these markets, which are then used to determine and explore portfolio design and hedging implications. The results show that while bidirectional return spillovers between the main and SME stock markets are limited to Saudi Arabia, shock and volatility spillovers have different characteristics and dynamics in both main–SME market pairs. In addition, the dynamic correlations between the main and SME markets are mostly positive and have notably increased during the COVID-19 pandemic, particularly in Saudi Arabia, suggesting that adding SME stocks to a main stock portfolio enhances its risk-adjusted return, especially during tranquil market phases. One practical implication of our results is that the development of SME stock markets can indirectly contribute to economic development via the main market channel and provide an avenue for portfolio diversification and risk management.

High-level cognition during story listening is reflected in high-order dynamic correlations in neural activity patterns

Our thoughts arise from coordinated patterns of interactions between brain structures that change with our ongoing experiences. High-order dynamic correlations in neural activity patterns reflect different subgraphs of the brain’s functional connectome that display homologous lower-level dynamic correlations. Here we test the hypothesis that high-level cognition is reflected in high-order dynamic correlations in brain activity patterns. We develop an approach to estimating high-order dynamic correlations in timeseries data, and we apply the approach to neuroimaging data collected as human participants either listen to a ten-minute story or listen to a temporally scrambled version of the story. We train across-participant pattern classifiers to decode (in held-out data) when in the session each neural activity snapshot was collected. We find that classifiers trained to decode from high-order dynamic correlations yield the best performance on data collected as participants listened to the (unscrambled) story. By contrast, classifiers trained to decode data from scrambled versions of the story yielded the best performance when they were trained using first-order dynamic correlations or non-correlational activity patterns. We suggest that as our thoughts become more complex, they are reflected in higher-order patterns of dynamic network interactions throughout the brain.

Spillovers and Dynamic Correlations between REITs, Exchange Rates, and Equities in Japan

This paper investigates return transmission, volatility spillovers, and dynamic correlations between the Tokyo Stock Exchange (TSE) Real Estate Investment Trust (REIT) index, the Nikkei 225 index, and the yen/dollar exchange rate. As a result, we find many new findings and these all show our significant contributions as follows. First, there is return transmission from the Nikkei 225 to the TSE REIT index. Second, there is bidirectional return transmission between the Nikkei 225 and the yen/dollar exchange rate. Third, there are bidirectional volatility spillovers between the Nikkei 225 and the TSE REIT index. Fourth, there are volatility spillovers from the Nikkei 225 to the yen/dollar exchange rate. Fifth, dynamic conditional correlations (DCCs) between TSE REIT returns and Nikkei 225 returns are not low. Moreover, DCCs between Nikkei 225 returns and yen/dollar exchange rate changes are not high. Furthermore, DCCs between TSE REIT returns and yen/dollar exchange rate changes are quite low. These our new findings shall be useful for not only deepening our understanding of financial markets but also our related future research.

Green Bonds and Asset Classes: New Evidence from Time-varying Copula and Transfer Entropy Models

The green bond market has gradually developed worldwide since its debut in 2007 and is viewed as a new form of investment. This study explores the time-varying interdependence between green bond and conventional asset classes, namely Bitcoin price, Standard and Poor’s (S&P) 500, Clean Energy Index, Goldman Sachs Commodity Index (GSCI) Commodity Index and 10-year US bond spanning from May 2013 to December 2019, using both time-varying copula and transfer entropy models. We first focus on static and dynamic correlations between the green bond and other assets, and then identify the causal association among them. The findings suggest that green bonds and other assets have conditional time-varying dependence, and dependence is relatively low. Using transfer entropy, further evidence is gained for causal associations between two variables, which is depicted by two categories like mono-direction and bi-direction. Such nexus reveals the transmitter and receiver of return innovations on these markets. These findings make a considerable contribution to policymakers and environmentally friendly investors with green bond positions.

ISSUES OF THE RELATIONSHIP BETWEEN THE STATE BUDGET AND ECONOMIC GROWTH IN UZBEKISTAN

The article examines the interaction of the country's GDP with the state budget in the short and long term, the impact of the macro-fiscal mechanism on the country's economic growth on the example of Uzbekistan.The aim of the study is to identify dynamic correlations between the country's state budget expenditures and the economic growth of the macro-fiscal mechanism in the short and long term, as well as to analyze the approximation or rate of return of GDP and the state budget to equilibrium during various macroeconomic shocks. and hesitation.The scientific novelties of the research are: