No abstract

Traditional stock market prediction approaches commonly utilize the historical price-related data of the stocks to forecast their future trends. As the Web information grows, recently some works try to explore financial news to improve the prediction. Effective indicators, e.g., the events related to the stocks and the people's sentiments towards the market and stocks, have been proved to play important roles in the stocks' volatility, and are extracted to feed into the prediction models for improving the prediction accuracy. However, a major limitation of previous methods is that the indicators are obtained from only a single source whose reliability might be low, or from several data sources but their interactions and correlations among the multi-sourced data are largely ignored.In this work, we extract the events from Web news and the users' sentiments from social media, and investigate their joint impacts on the stock price movements via a coupled matrix and tensor factorization framework. Specifically, a tensor is firstly constructed to fuse heterogeneous data and capture the intrinsic * Corresponding author relations among the events and the investors' sentiments. Due to the sparsity of the tensor, two auxiliary matrices, the stock quantitative feature matrix and the stock correlation matrix, are constructed and incorporated to assist the tensor decomposition. The intuition behind is that stocks that are highly correlated with each other tend to be affected by the same event. Thus, instead of conducting each stock prediction task separately and independently, we predict multiple correlated stocks simultaneously through their commonalities, which are enabled via sharing the collaboratively factorized low rank matrices between matrices and the tensor. Evaluations on the China A-share stock data and the HK stock data in the year 2015 demonstrate the effectiveness of the proposed model.

Previous studies have shown a relationship between type 2 diabetes mellitus and birth weight. We performed this meta-analysis to resolve the problem of inconsistent results. We conducted a literature search of PubMed, Embase and the Cochrane Library using "Diabetes Mellitus, Type 2," "Birth Weight," and some related free words. Twenty-one studies were included in accordance with inclusion and exclusion criteria, involving a total of 313,165 participants and 22,341 type 2 diabetes mellitus cases. A modified version of the Newcastle-Ottawa Scale was used to evaluate the methodological quality of studies included. We used Review Manager 5.3 for data merging and statistical analysis. Results were expressed as odds ratio (OR) and 95% confidence interval (95% CI). The risk of diabetes with low birth weight (<2,500 g) was higher than that with birth weight ≥2,500 g, (OR = 1.51, 95% CI: 1.43, 1.58). Compared with normal birth weight (2,500-4,000 g), low birth weight, but not high birth weight, increased the risk of diabetes (OR = 1.41, 95% CI: 1.26, 1.58). There is a negative association between birth weight and the future risk of type 2 diabetes mellitus.

Objective: Few studies have considered the effect of resveratrol on blood lipid levels, and the results of these studies are inconsistent. In this study, the first meta-analysis on the effect of resveratrol on blood lipid levels in patients with type 2 diabetes was conducted. Methods: This study used keywords such as type 2 diabetes, total cholesterol, triglyceride (TG), high-density lipoprotein, low-density lipoprotein, and resveratrol and their abbreviations, free words, and related words to search PubMed, Cochrane Library, and Embase. The Cochrane risk of bias tool was used to evaluate the risk of bias, and Review Manager 5.3 and Stata 13.0 were used for data merging and statistical analysis. Results: Ten randomized controlled trials involving a total of 363 patients with type 2 diabetes were included in the analysis. The results show that longer resveratrol intervention time (≥6 months) can reduce TG levels. But resveratrol increased total cholesterol in patients within obesity range. In type 2 diabetes patients with obesity and in those who took lipid-lowering drugs, resveratrol increased low-density lipoprotein levels. Conclusions: Resveratrol can improve TG in patients with type 2 diabetes.