In this report, I present a deep learning approach to conduct a natural
language processing (hereafter NLP) binary classification task for analyzing
financial-fraud texts. First, I searched for regulatory announcements and
enforcement bulletins from HKEX news to define fraudulent companies and to
extract their MD&A reports before I organized the sentences from the reports
with labels and reporting time. My methodology involved different kinds of
neural network models, including Multilayer Perceptrons with Embedding layers,
vanilla Recurrent Neural Network (RNN), Long-Short Term Memory (LSTM), and
Gated Recurrent Unit (GRU) for the text classification task. By utilizing this
diverse set of models, I aim to perform a comprehensive comparison of their
accuracy in detecting financial fraud. My results bring significant
implications for financial fraud detection as this work contributes to the
growing body of research at the intersection of deep learning, NLP, and
finance, providing valuable insights for industry practitioners, regulators,
and researchers in the pursuit of more robust and effective fraud detection
methodologies.

使用深度学习的方法对金融欺诈文本进行自然语言处理的二元分类任务，并且通过不同种类的神经网络模型，包括多层感知机、RNN、LSTM 和 GRU 等，进行了准确性比较，为金融欺诈检测领域提供了有价值的见解。

金融欺诈检测的文本数据挖掘：深度学习方法

Textual Data Mining for Financial Fraud Detection: A Deep Learning  Approach

To produce important investment decisions, investors require financial
records and economic information. However, most companies manipulate investors
and financial institutions by inflating their financial statements. Fraudulent
Financial Activities exist in any monetary or financial transaction scenario,
whether physical or electronic. A challenging problem that arises in this
domain is the issue that affects and troubles individuals and institutions.
This problem has attracted more attention in the field in part owing to the
prevalence of financial fraud and the paucity of previous research. For this
purpose, in this study, the main approach to solve this problem, an anomaly
detection-based approach based on a combination of feature selection based on
squirrel optimization pattern and classification methods have been used. The
aim is to develop this method to provide a model for detecting anomalies in
financial statements using a combination of selected features with the nearest
neighbor classifications, neural networks, support vector machine, and
Bayesian. Anomaly samples are then analyzed and compared to recommended
techniques using assessment criteria. Squirrel optimization's meta-exploratory
capability, along with the approach's ability to identify abnormalities in
financial data, has been shown to be effective in implementing the suggested
strategy. They discovered fake financial statements because of their expertise.

本研究基于松鼠优化模式的特征选择结合分类方法，旨在提供一个模型来检测财务报表中的异常情况，并比较分析异常样本，研究发现该方法能够有效地实现建议的策略，发现了假财务报表。

利用优化算法和基于松鼠的分类技术挑选一组特征以检测欺诈性财务文件

Detection of fraudulent financial papers by picking a collection of characteristics using optimization algorithms and classification techniques based on squirrels

We consider a novel queuing problem where the decision-maker must choose to
accept or reject randomly arriving tasks into a no buffer queue which are
processed by $N$ identical servers. Each task has a price, which is a positive
real number, and a class. Each class of task has a different price distribution
and service rate, and arrives according to an inhomogenous Poisson process. The
objective is to decide which tasks to accept so that the total price of tasks
processed is maximised over a finite horizon. We formulate the problem as a
discrete time Markov Decision Process (MDP) with a hybrid state space. We show
that the optimal value function has a specific structure, which enables us to
solve the hybrid MDP exactly. Moreover, we prove that as the time step is
reduced, the discrete time solution approaches the optimal solution to the
original continuous time problem. To improve the scalability of our approach to
a greater number of task classes, we present an approximation based on state
abstraction. We validate our approach on synthetic data, as well as a real
financial fraud data set, which is the motivating application for this work.

本文提出一个新的排队问题，该问题涉及价格、不同的价格分布和服务速率的任务，提出了一种基于强化学习的方法。实验表明，该方法适用于金融欺诈检测。