Innovative deep matching algorithm for stock portfolio selection using deep stock profiles.

Construction of a reliable stock portfolio remains an open issue in quantitative investment. Multiple machine learning models have been trained for stock portfolio selection, but their practical applicability remains limited due to the challenges posed by the characteristic of a low signal-to-noise ratio (SNR), the nature of time-series data, and non-independent identical distribution in financial data. Here, we transformed the stock selection task into a matching problem between a group of stocks and a stock selection target. We proposed a novel representation algorithm of stock selection target and a novel deep matching algorithm (TS-Deep-LtM). Then we proposed a deep stock profiling method to extract the optimal feature combination and trained a deep matching model based on TS-Deep-LtM algorithm for stock portfolio selection. Especially, TS-Deep-LtM algorithm was obtained by setting statistical indicators to filter and integrate three deep text matching algorithms. This parallel framework design made it good at capturing signals from time-series data and adapting to non-independent identically distributed data. Finally, we applied the proposed model to stock selection and tested long-only portfolio strategies from 2010 to 2017. We demonstrated that the risk-adjusted returns obtained by our portfolio strategies outperformed those obtained by the CSI300 index and learning-to-rank approaches during the same period.

A deep learning framework for financial time series using stacked autoencoders and long-short term memory.

The application of deep learning approaches to finance has received a great deal of attention from both investors and researchers. This study presents a novel deep learning framework where wavelet transforms (WT), stacked autoencoders (SAEs) and long-short term memory (LSTM) are combined for stock price forecasting. The SAEs for hierarchically extracted deep features is introduced into stock price forecasting for the first time. The deep learning framework comprises three stages. First, the stock price time series is decomposed by WT to eliminate noise. Second, SAEs is applied to generate deep high-level features for predicting the stock price. Third, high-level denoising features are fed into LSTM to forecast the next day's closing price. Six market indices and their corresponding index futures are chosen to examine the performance of the proposed model. Results show that the proposed model outperforms other similar models in both predictive accuracy and profitability performance.

An experimental analysis of acquired impulse control among adult humans intolerant to alcohol.

The ability to control tempting impulses impacts health, education, and general socioeconomic outcomes among people at all ages. Consequently, whether and how impulse control develops in adult populations is a topic of enduring interest. Although past research has shed important light on this question using controlled intervention studies, here we take advantage of a natural experiment in China, where males but not females encounter substantial social pressure to consume alcohol. One-third of our sample, all of whom are Han Chinese, is intolerant to alcohol, whereas the remaining control sample is observationally identical but alcohol tolerant. Consistent with previous literature, we find that intolerant males are significantly more likely to exercise willpower to limit their alcohol consumption than alcohol-tolerant males. In view of the strength model of self-control, we hypothesize that this enables improved impulse control in other contexts as well. To investigate this hypothesis, we compare decisions in laboratory games of self-control between the tolerant and intolerant groups. We find that males intolerant to alcohol and who regularly encounter drinking environments control their selfish impulses significantly better than their tolerant counterparts. On the other hand, we find that female Han Chinese intolerant to alcohol do not use self-control to limit alcohol consumption more than tolerant females, nor do the tolerant and intolerant females exhibit differences in self-control behaviors. Our research indicates that impulse control can be developed in adult populations as a result of self-control behaviors in natural environments, and shows that this skill has generalizable benefits across behavioral domains.