In recent years, a variety of research fields, including finance, have begun to place great emphasis on machine learning techniques because they exhibit broad abilities to simulate more complicated problems. In contrast to the traditional linear regression scheme that is usually used to describe the relationship between the stock forward return and company characteristics, the field of finance has experienced the rapid development of tree-based algorithms and neural network paradigms when illustrating complex stock dynamics. These nonlinear methods have proved to be effective in predicting stock prices and selecting stocks that can outperform the general market. This article implements and evaluates the robustness of the random forest (RF) model in the context of the stock selection strategy. The model is trained for stocks in the Chinese stock market, and two types of feature spaces, fundamental/technical feature space and pure momentum feature space, are adopted to forecast the price trend in the long run and the short run, respectively. It is evidenced that both feature paradigms have led to remarkable excess returns during the past five out-of-sample period years, with the Sharpe ratios calculated to be 2.75 and 5 for the portfolio net value of the multi-factor space strategy and momentum space strategy, respectively. Although the excess return has weakened in recent years with respect to the multi-factor strategy, our findings point to a less efficient market that is far from equilibrium.

Adversarial generative models are becoming an essential tool in molecular design and discovery due to their efficiency in exploring the desired chemical space with the assistance of deep learning. In this article, we introduce an integrated framework by combining the modules of algorithmic synthesis, deep prediction, adversarial generation, and fine screening for the purpose of effective design of the thermally activated delayed fluorescence (TADF) molecules that can be used in the organic light-emitting diode devices. The retrosynthetic rules are employed to algorithmically synthesize the D–A complex based on the empirically defined donor and acceptor moieties, which is followed by the high-throughput labeling and prediction with the deep neural network. The new D–A molecules are subsequently generated via the adversarial autoencoder, with the excited-state property distributions perfectly matching those of the original samples. Fine screening of the generated molecules, including the spin–orbital coupling calculation and the excited-state optimization, is eventually implemented to select the qualified TADF candidates within the novel chemical space. Further investigation shows that the created structures fully mimic the original D–A samples by maintaining a significant charge transfer characteristic, a minimal adiabatic singlet–triplet gap, and a moderate spin–orbital coupling that are desirable for the delayed fluorescence.

No abstract

The development of AI for fluorescent materials design is technologically demanding due to the issue of accurately forecasting fluorescent properties.

The endeavors to pursue a robust multitask model to resolve intertask correlations have lasted for many years. A multitask deep neural network, as the most widely used multitask framework, however, experiences several issues such as inconsistent performance improvement over the independent model benchmark. The research aims to introduce an alternative framework by using the problem transformation methods. We build our multitask models essentially based on the stacking of a base regressor and classifier, where the multitarget predictions are realized from an additional training stage on the expanded molecular feature space. The model architecture is implemented on the QM9, Alchemy, and Tox21 datasets, by using a variety of baseline machine learning techniques. The resultant multitask performance shows 1 to 10% enhancement of forecasting precision, with the task prediction accuracy being consistently improved over the independent single-target models. The proposed method demonstrates a notable superiority in tackling the intertarget dependence and, moreover, a great potential to simulate a wide range of molecular properties under the transformation framework.