In this paper, we propose a simple yet efficient instance-wise graph-based framework to utilize the inter-dependencies of different variables at different time stamps for multivariate time series forecasting.
Modeling and managing portfolio risk is perhaps the most important step to achieve growing and preserving investment performance.
In this paper, we propose a novel architecture, Temporal Routing Adaptor (TRA), to empower existing stock prediction models with the ability to model multiple stock trading patterns.
To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts.
As a fundamental problem in algorithmic trading, order execution aims at fulfilling a specific trading order, either liquidation or acquirement, for a given instrument.
For wait-k inference, we observe that wait-m training with $m>k$ in simultaneous NMT (i. e., using more future information for training than inference) generally outperforms wait-k training.
Stock trend forecasting has become a popular research direction that attracts widespread attention in the financial field.
Quantitative investment aims to maximize the return and minimize the risk in a sequential trading period over a set of financial instruments.
In many applications, a sequence learning task is usually associated with multiple temporally correlated auxiliary tasks, which are different in terms of how much input information to use or which future step to predict.
Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc.
Our results demonstrate that the occurrence of overfitting is positively correlated with the increase of model complexity during training.
Stock trend prediction plays a critical role in seeking maximized profit from stock investment.