Online portfolio management via deep reinforcement learning with high-frequency data

Recently, models that based on Transformer (Vaswani et al., 2017) have yielded superior results in many sequence modeling tasks. The ability of Transformer to capture long-range dependencies and interactions makes it possible to apply it in the field of portfolio management (PM). However, the built-in quadratic complexity of the Transformer prevents its direct application to the PM task. To solve this problem, in this paper, we propose a deep reinforcement learning-based PM framework called LSRE-CAAN, with two important components: a long sequence representations extractor and a cross-asset attention network. Direct Policy Gradient is used to solve the sequential decision problem in the PM process. We conduct numerical experiments in three aspects using four different cryptocurrency datasets, and the empirical results show that our framework is more effective than both traditional and state-of-the-art (SOTA) online portfolio strategies, achieving a 6x return on the best dataset. In terms of risk metrics, our framework has an average volatility risk of 0.46 and an average maximum drawdown risk of 0.27 across the four datasets, both of which are lower than the vast majority of SOTA strategies. In addition, while the vast majority of SOTA strategies maintain a poor turnover rate of approximately greater than 50% on average, our framework enjoys a relatively low turnover rate on all datasets, efficiency analysis illustrates that our framework no longer has the quadratic dependency limitation.     

中文科技政策文本分类：增强的TextCNN视角*

近年尽管针对中文本文分类的研究成果不少,但基于深度学习对中文政策等长文本进行自动分类的研究还不多见。为此,借鉴和拓展传统的数据增强方法,提出集成新时代人民日报分词语料库（NEPD）、简单数据增强（EDA）算法、word2vec和文本卷积神经网络（TextCNN）的NEWT新型计算框架;实证部分,基于中国地方政府发布的科技政策文本进行算法校验。实验结果显示,在取词长度分别为500、750和1 000词的情况下,应用NEWT算法对中文科技政策文本进行分类的效果优于RCNN、Bi-LSTM和CapsNet等传统深度学习模型,F1值的平均提升比例超过13%;同时,NEWT在较短取词长度下能够实现全文输入的近似效果,可以部分改善传统深度学习模型在中文长文本自动分类任务中的计算效率。     

A Recursive tree-structured neural network with goal forgetting and information aggregation for solving math word problems

Most existing state-of-the-art neural network models for math word problems use the Goal-driven Tree-Structured decoder (GTS) to generate expression trees. However, we found that GTS does not provide good predictions for longer expressions, mainly because it does not capture the relationships among the goal vectors of each node in the expression tree and ignores the position order of the nodes before and after the operator. In this paper, we propose a novel Recursive tree-structured neural network with Goal Forgetting and information aggregation (RGFNet) to address these limits. The goal forgetting and information aggregation module is based on ordinary differential equations (ODEs) and we use it to build a sub-goal information feedback neural network (SGIFNet). Unlike GTS, which uses two-layer gated-feedforward networks to generate goal vectors, we introduce a novel sub-goal generation module. The sub-goal generation module could capture the relationship among the related nodes (e.g. parent nodes, sibling nodes) using attention mechanism. Experimental results on two large public datasets i.e. Math23K and Ape-clean show that our tree-structured model outperforms the state-of-the-art models and obtains answer accuracy over 86%. Furthermore, the performance on long-expression problems is promising.¹     

Data and infrastructure security auditing in cloud computing environments

For many companies the remaining barriers to adopting cloud computing services are related to security. One of these significant security issues is the lack of auditability for various aspects of security in the cloud computing environment. In this paper we look at the issue of cloud computing security auditing from three perspectives: user auditing requirements, technical approaches for (data) security auditing and current cloud service provider capabilities for meeting audit requirements. We also divide specific auditing issues into two categories: infrastructure security auditing and data security auditing. We find ultimately that despite a number of techniques available to address user auditing concerns in the data auditing area, cloud providers have thus far only focused on infrastructure security auditing concerns.     

On the feasibility of Federated Learning towards on-demand client deployment at the edge

Nowadays, researchers are investing their time and devoting their efforts in developing and motivating the 6G vision and resources that are not available in 5G. Edge computing and autonomous vehicular driving applications are more enhanced under the 6G services that are provided to successfully operate tasks. The huge volume of data resulting from such applications can be a plus in the AI and Machine Learning (ML) world. Traditional ML models are used to train their models on centralized data sets. Lately, data privacy becomes a real aspect to take into consideration while collecting data. For that, Federated Learning (FL) plays nowadays a great role in addressing privacy and technology together by maintaining the ability to learn over decentralized data sets. The training is limited to the user devices only while sharing the locally computed parameter with the server that aggregates those updated weights to optimize a global model. This scenario is repeated multiple rounds for better results and convergence. Most of the literature proposed client selection methods to converge faster and increase accuracy. However, none of them has targeted the ability to deploy and select clients in real-time wherever and whenever needed. In fact, some mobile and vehicular devices are not available to serve as clients in the FL due to the highly dynamic environments and/or do not have the capabilities to accomplish this task. In this paper, we address the aforementioned limitations by introducing an on-demand client deployment in FL offering more volume and heterogeneity of data in the learning process. We make use of containerization technology such as Docker to build efficient environments using any type of client devices serving as volunteering devices, and Kubernetes utility called Kubeadm to monitor the devices. The performed experiments illustrate the relevance of the proposed approach and the efficiency of the deployment of clients whenever and wherever needed.     

Evaluating the generalisability of neural rumour verification models

Research on automated social media rumour verification, the task of identifying the veracity of questionable information circulating on social media, has yielded neural models achieving high performance, with accuracy scores that often exceed 90%. However, none of these studies focus on the real-world generalisability of the proposed approaches, that is whether the models perform well on datasets other than those on which they were initially trained and tested. In this work we aim to fill this gap by assessing the generalisability of top performing neural rumour verification models covering a range of different architectures from the perspectives of both topic and temporal robustness. For a more complete evaluation of generalisability, we collect and release COVID-RV, a novel dataset of Twitter conversations revolving around COVID-19 rumours. Unlike other existing COVID-19 datasets, our COVID-RV contains conversations around rumours that follow the format of prominent rumour verification benchmarks, while being different from them in terms of topic and time scale, thus allowing better assessment of the temporal robustness of the models. We evaluate model performance on COVID-RV and three popular rumour verification datasets to understand limitations and advantages of different model architectures, training datasets and evaluation scenarios. We find a dramatic drop in performance when testing models on a different dataset from that used for training. Further, we evaluate the ability of models to generalise in a few-shot learning setup, as well as when word embeddings are updated with the vocabulary of a new, unseen rumour. Drawing upon our experiments we discuss challenges and make recommendations for future research directions in addressing this important problem.     

一种图像边缘提取快速KIRSCH算子的设计与实现

对前人提出的数字图像边缘的经典算子--kirsch算子进行研究,详细分析了这种方法的出发点、理论根据、数学原理和实现方法及优缺点。并通过用Visual C++实现的实验结果,对kirsch算法提出了改进,实现了改进的快速kirsch算子的边缘提取,给出了对于一般图像的处理效果的分析。     

Forecasting movements of stock time series based on hidden state guided deep learning approach

Stock movement forecasting is usually formalized as a sequence prediction task based on time series data. Recently, more and more deep learning models are used to fit the dynamic stock time series with good nonlinear mapping ability, but not much of them attempt to unveil a market system’s internal dynamics. For instance, the driving force (state) behind the stock rise may be the company’s good profitability or concept marketing, and it is helpful to judge the future trend of the stock. To address this issue, we regard the explored pattern as an organic component of the hidden mechanism. Considering the effective hidden state discovery ability of the Hidden Markov Model (HMM), we aim to integrate it into the training process of the deep learning model. Specifically, we propose a deep learning framework called Hidden Markov Model-Attentive LSTM (HMM-ALSTM) to model stock time series data, which guides the hidden state learning of deep learning methods via the market’s pattern (learned by HMM) that generates time series data. What is more, a large number of experiments on 6 real-world data sets and 13 stock prediction baselines for predicting stock movement and return rate are implemented. Our proposed HMM-ALSTM achieves an average 10% improvement on all data sets compared to the best baseline.