Predicting the daily return direction of the stock market using hybrid machine learning algorithms

Big data analytic techniques associated with machine learning algorithms are playing an increasingly important role in various application fields,including stock market investment.However,few studies have focused on forecasting daily stock market returns,especially when using powerful machine learning techniques,such as deep neural networks(DNNs),to perform the analyses.DNNs employ various deep learning algorithms based on the combination of network structure,activation function,and model parameters,with their performance depending on the format of the data representation.This paper presents a comprehensive big data analytics process to predict the daily return direction of the SPDR S&P 500 ETF(ticker symbol:SPY)based on 60 financial and economic features.DNNs and traditional artificial neural networks(ANNs)are then deployed over the entire preprocessed but untransformed dataset,along with two datasets transformed via principal component analysis(PCA),to predict the daily direction of future stock market index returns.While controlling for overfitting,a pattern for the classification accuracy of the DNNs is detected and demonstrated as the number of the hidden layers increases gradually from 12 to 1000.Moreover,a set of hypothesis testing procedures are implemented on the classification,and the simulation results show that the DNNs using two PCA-represented datasets give significantly higher classification accuracy than those using the entire untransformed dataset,as well as several other hybrid machine learning algorithms.In addition,the trading strategies guided by the DNN classification process based on PCA-represented data perform slightly better than the others tested,including in a comparison against two standard benchmarks.

Return direction forecasting:a conditional autoregressive shape model with beta density

This paper derives a new decomposition of stock returns using price extremes and proposes a conditional autoregressive shape(CARS)model with beta density to predict the direction of stock returns.The CARS model is continuously valued,which makes it different from binary classification models.An empirical study is performed on the US stock market,and the results show that the predicting power of the CARS model is not only statistically significant but also economically valuable.We also compare the CARS model with the probit model,and the results demonstrate that the proposed CARS model outperforms the probit model for return direction forecasting.The CARS model provides a new framework for return direction forecasting.

Directional congestion in the framework of data envelopment analysis

This studyfirst proposes a definition for directional congestion in certain input and output directions within the framework of data envelopment analysis.Second,two methods from different viewpoints are proposed to estimate the directional congestion.Third,we address the relationship between directional congestion and classic(strong or weak)congestion.Finally,we present a case study investigating the analysis performed by the research institutes of the Chinese Academy of Sciences to demonstrate the applicability and usefulness of the methods developed in this study.

Stability Analysis of Closed-loop Water System

Aiming at closed-loop water system, by the method that shutting certain subcircuit, and solving the piping network, computing flow deviation of other subcircuits, then analyzing the rules of variation of stability with various factors, following conclusions are obtained： When reducing the resistance in main pipes, increasing resistance of subcircuits, system stability can be improved. Centralized regulation by changing power has no influence on system stability; centralized regulation by changing resistances will decrease system stability. Pump characteristics curve influences system stability, stability of the flat characteristic is superior to the steep one. For direct return system （DRS）, the stability of subcircuit which is farthest from the heat source is the worst. For reverse return system （RRS）, the stability of subcircuit in the middle of the pipe-network has the worst stability. Overall, stability of RRS is inferior to that of DRS.

A discussion of Hong-Stein model

In this paper,we discuss a kind of behavioral asset pricing model,called Hong-Stein model.Although this model succeeded in explaining the momentum and reversal effects,we find it usually reaches two extremes:the absolute value of autocorrelation of return sequence is so large that the direction of returns could be easily forecasted,or the value is so small that the elements in return sequence are almost independent of each other.The empirical results show that these two extremes are not supported by the real market data.

Real-time observation of liquid crystal molecular directions based on a snapshot polarimeter

The polarization state of transmitted light is linked to liquid crystal（LC） molecular distribution. The dynamic behavior of a twisted nematic LC molecule is measured with a home-built 10 k Hz snapshot polarimeter. Only the transient molecule rotations are observed when the external voltage changes, and the molecules return to their original orientations quickly even when high voltage is applied. Our observations cannot be attributed to the traditional electro-optic effect. The invalidation of the static external field indicates the shielding effect of redistributing impurity ions in an LC cell.