Machine learning for financial transaction classification across companies using character-level word embeddings of text fields

An important initial step in accounting is mapping financial transfers to the corresponding accounts. We devised machine-learning-based systems that automate this process. They use word embeddings with character-level features to process transaction texts. When considering 473 companies independently, our approach achieved an average top-1 accuracy of 80.50%, outperforming baselines that exclude the transaction texts or rely on a lexical bag-of-words text representation. We extended the approach to generalizes across companies and even across different corporate sectors. After standardization of the account structures and careful feature engineering, a single classifier trained on 44 companies from 28 sectors achieved a test accuracy of more than 80%. When trained on 43 companies and tested on the remaining one, the system achieved an average performance of 64.62%. This rate increased to nearly 70% when considering only the largest sector.     

Application of collective knowledge diffusion in a social network environment

ABSTRACT

We present a group dynamics model that shows knowledge integration as a process occurring over time. As each individual in the group contact others, his own knowledge changes, and over time the collective knowledge is obtained. This allows modeling knowledge diffusion in a social network and while the models presented in this paper are not competitive in that area, they approach the problem from previously unconsidered direction. We test the behavior of the model in a multi-agent simulation and we test a simple advertisement campaign in a social network. We provide discussion of elements needed for making model more competitive.     

Financial scandals: a historical overview

I examine the incidence of fraud from c.1720 to 2009 and relate it to the occurrence of significant financial scandals. Focusing on the UK, and US prior to Enron, and using a detailed dataset of significant events and news content, underpinned by examination of specific watershed scandals, the paper highlights the regulatory response to scandals and the implications for accounting and financial reporting. The evidence reveals the incidence of fraud and financial scandal to be historically contingent and skewed towards certain sectors, particularly banking and finance, facilitated by complex group structures and international capital mobility, and mediated by managerial incentives and ownership concentration. Financial reporting and auditing can mitigate fraud opportunities in all sectors and businesses without complex group structures, and the accounting profession achieved some success in this respect up to the mid-1970s. Since then, the profession has been increasingly challenged by, and to some degree implicated in, the development of interconnected and international business networks, which, combined with wider financial deregulation, has led to a resurgence of fraud and financial scandal not previously experienced since the mid-nineteenth century.     

Organizational versus Market Knowledge: From Concrete Embodiment to Abstract Representation

Synopsis In contrast to the neoclassical economic presumption in favor of markets, we argue that organizations, not markets should be taken as our default assumption. We do so on information processing grounds. We distinguish between Zen and market Knowledge. The first is embodied and hard to articulate and the second abstract-symbolic. In human evolution, the first type of knowledge came first, and, on any pragmatic definition of knowledge, it still incorporates most of what we mean by the term. We take codification and abstraction as the two data processing activities that lead to the articulation of knowledge into an abstract-symbolic form. We develop a conceptual framework, the Information-Space (I-Space) to show how far the articulation of knowledge leads to its being shared. Whereas an unlimited sharing of information and knowledge leads to market-oriented outcomes, a more limited sharing leads to organizational outcomes. A market-oriented economics has tended to look to physics for its models; the field of organization theory has tended to look to biology. A more organization-oriented economics would thus look more to biology for its models.     

加强会计诚信建设 提高会计信息质量

会计信息是国家的宏观经济管理部门、企业经济管理部门及其他方面进行决策的依据。会计信息真实客观与否，直接影响着企业经营管理、国家宏观调控、广大股东的投资决策，势必影响市场经济的有效健康发展。从根本上建立一套与市场经济相适应的会计信息质量保障体系势在必行，而整个体系的建立和健全是一个任重而道远的过程。在这个过程中，会计诚信也成了整个市场经济发展的职业道德规范，笔者就此谈谈几点看法。     

试论二元经济形态下的会计模式

本文分析了在知识经济兴起的环境下我国现行会计模式存在的缺陷,并根据知识经济发展的历程以及我国目前工业经济与知识经济并存的现状,提出了一种能适应两种经济形态的兼容性会计模式,最后指出了目前实施该模式尚存在的制约因素。     

高校财务实行内部会计控制的几点思考

分析了高校实施内部会计控制的背景和存在的主要问题,表述了对高校内部会计控制的方法和关键控制点,提出了解决目前高校内部会计控制存在问题的解决方法和主要对策.     

试析中小型民营家族制企业财务管理问题及对策

近几年来,民营经济在我国经济中的地位越来越突出。该文在分析家族制管理模式的利弊及其对企业财务管理影响的基础上,对中小型民营家族制企业财务管理存在的问题及改善对策进行了探讨。     

会计专业毕业生面向有色金属行业就业的探索和实践

有色金属行业是我国国民经济的重要组成部分，直接影响到国家经济的发展和社会的稳定。根据有色金属行业的特点，鼓励和引导优秀毕业生到基层，到祖国需要的地方去，满足有色金属行业对人才的迫切需求，探索一条会计专业毕业生面向有色金属行业就业新途径。     

企业知识管理绩效综合评价案例研究

知识管理是现代企业管理的重要内容。正确分析和评价企业的知识管理绩效，对于促进企业知识管理、提高企业知识管理水平以及增强企业竞争优势，具有重要的现实意义。文章构建了企业知识管理绩效评价的指标体系，并运用模糊综合评价模型对企业知识管理绩效进行了综合评价。