Stock Market Forecasting Based on Spatiotemporal Deep Learning.

This study introduces the Spacetimeformer model, a novel approach for predicting stock prices, leveraging the Transformer architecture with a time-space mechanism to capture both spatial and temporal interactions among stocks. Traditional Long-Short Term Memory (LSTM) and recent Transformer models lack the ability to directly incorporate spatial information, making the Spacetimeformer model a valuable addition to stock price prediction. This article uses the ten minute stock prices of the constituent stocks of the Taiwan 50 Index and the intraday data of individual stock on the Taiwan Stock Exchange. By training the Timespaceformer model with multi-time-step stock price data, we can predict the stock prices at every ten minute interval within the next hour. Finally, we also compare the prediction results with LSTM and Transformer models that only consider temporal relationships. The research demonstrates that the Spacetimeformer model consistently captures essential trend changes and provides stable predictions in stock price forecasting. This article proposes a Spacetimeformer model combined with daily moving windows. This method has superior performance in stock price prediction and also demonstrates the significance and value of the space-time mechanism for prediction. We recommend that people who want to predict stock prices or other financial instruments try our proposed method to obtain a better return on investment.

Activin A induction of erythroid differentiation through MKK6-p38alpha/p38beta pathway is inhibited by follistatin.

Activin A is a member of the transforming growth factor (TGF)-beta superfamily that regulates cell proliferation and differentiation. Using the p38 inhibitor SB203580, our previous studies demonstrated that p38 was involved in activin A-mediated hemoglobin (Hb) synthesis in K562 cells. SB203580 is an inhibitor of p38alpha and p38beta isoforms. In this study, we show that p38alpha and p38beta mRNA were expressed in K562 cells and that activin A activated the kinase activities of these isoforms. To investigate the roles of p38alpha and p38beta isoforms in activin A-mediated erythroid differentiation, we generated stable clones that over-expressed the dominant negative p38 isoforms p38alpha(AF) and p38beta(AF) in K562 cells. The expressions of either p38alpha(AF) or p38beta(AF) reduced activin A-induced p38 activation, Hb synthesis, and zeta-globin promoter activity. Similarly, down-regulation of either p38alpha or p38beta by isoform-specific siRNAs also reduced activin A-induced zeta-globin promoter activity. Co-expressions of p38alpha(AF) and p38beta(AF), together, greatly inhibited the transcription activity of the zeta-globin promoter. Conversely, expression of mitogen-activated protein kinase kinase (MKK) 6b(E), a constitutive activator of p38, significantly activated zeta-globin promoter. Co-expressions of either p38alpha or p38beta with MKK6b had a similar activation of zeta-globin promoter. Activin A induction of erythroid differentiation was inhibited by follistatin. Activin A-induced phosphorylation of MKK6 and p38 was also inhibited by follistatin. Moreover, over-expression of MKK6b(E) reverted follistatin inhibition of activin A-induced zeta-globin promoter activity. These results demonstrate that activin A induces erythroid differentiation of K562 cells through activation of MKK6-p38alpha/p38beta pathway and follistatin inhibits those effects.