Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
67
result(s) for
"Yen, Jerome"
Sort by:
Sentiment Analysis of Review Data Using Blockchain and LSTM to Improve Regulation for a Sustainable Market
E-commerce has developed greatly in recent years, as such, its regulations have become one of the most important research areas in order to implement a sustainable market. The analysis of a large amount of reviews data generated in the shopping process can be used to facilitate regulation: since the review data is short text and it is easy to extract the features through deep learning methods. Through these features, the sentiment analysis of the review data can be carried out to obtain the users’ emotional tendency for a specific product. Regulators can formulate reasonable regulation strategies based on the analysis results. However, the data has many issues such as poor reliability and easy tampering at present, which greatly affects the outcome and can lead regulators to make some unreasonable regulatory decisions according to these results. Blockchain provides the possibility of solving these problems due to its trustfulness, transparency and unmodifiable features. Based on these, the blockchain can be applied for data storage, and the Long short-term memory (LSTM) network can be employed to mine reviews data for emotional tendencies analysis. In order to improve the accuracy of the results, we designed a method to make LSTM better understand text data such as reviews containing idioms. In order to prove the effectiveness of the proposed method, different experiments were used for verification, with all results showing that the proposed method can achieve a good outcome in the sentiment analysis leading to regulators making better decisions.
Journal Article
A Novel Method for Food Market Regulation by Emotional Tendencies Predictions from Food Reviews Based on Blockchain and SAEs
As a part of food safety research, researches on food transactions safety has attracted increasing attention recently. Food choice is an important factor affecting food transactions safety: It can reflect consumer preferences and provide a basis for market regulation. Therefore, this paper proposes a food market regulation method based on blockchain and a deep learning model: Stacked autoencoders (SAEs). Blockchain is used to ensure the fairness of transactions and achieve transparency within the transaction process, thereby reducing the complexity of the trading environment. In order to enhance the usability, relevant Web pages have been developed to make it more friendly and conduct a security analysis for using blockchain. Consumers’ reviews after the transactions are finished can be used to train SAEs in order to perform emotional tendencies predictions. Compared with different advanced models for predictions, the test results show that SAEs have a better performance. Furthermore, in order to provide a basis for the formulation of regulation strategies and its related policies, case studies of different traders and commodities have also been conducted, proving the effectiveness of the proposed method.
Journal Article
Volatility Surface and Term Structure
This book provides different financial models based on options to predict underlying asset price and design the risk hedging strategies. Authors of the book have made theoretical innovation to these models to enable the models to be applicable to real market. The book also introduces risk management and hedging strategies based on different criterions. These strategies provide practical guide for real option trading.
This book studies the classical stochastic volatility and deterministic volatility models. For the former, the classical Heston model is integrated with volatility term structure. The correlation of Heston model is considered to be variable. For the latter, the local volatility model is improved from experience of financial practice. The improved local volatility surface is then used for price forecasting. VaR and CVaR are employed as standard criterions for risk management. The options trading strategies are also designed combining different types of options and they have been proven to be profitable in real market.
This book is a combination of theory and practice. Users will find the applications of these financial models in real market to be effective and efficient.
eBook
A novel method using LSTM-RNN to generate smart contracts code templates for improved usability
Recently, the development of blockchain technology has given us an opportunity to improve the security and trustworthiness of multimedia. With the applications of blockchain technology, smart contracts have been widely used in many industries. However, the current development of smart contracts faces many challenges. One of the challenges is that the coding process is complicated for developers, leading to unnormalized code and can cause development and maintenance issues. Also, this is an important limitation factor in the development of smart contracts. To solve this problem, this paper proposes a method of generating contract templates based on the Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) to simplify the coding process. First, the contracts available online were crawled, before detecting the vulnerabilities of these contracts. Contracts with less vulnerabilities are used as training data. For better generation effects, the Abstract Syntax Tree (AST) and the word2vec are used to extract the lexical unit sequence features to obtain a word vector in order to analyze the semantics of the code. Afterwards, the generated sequence vector features are fed to LSTM-RNN for template generation. The efficiency of four types of vectorization method models were tested and the results showed that the Skip-Gram+ HS used in this paper achieved the highest performance. In addition, a security test was conducted based on the contracts before and after using the contract templates for normalized coding. The results show that the proposed method is not only a beneficial attempt to combine deep learning with blockchain technology, but also provides an effective guidance for improving the security of smart contracts.
Journal Article
A method of customer valuation score and implementation for marketing strategy
PurposeThis study aims to introduce a compelling customer value score method (CVSM), which is applicable for different product categories, and elaborates customer values in three components (direct economic value, depth of direct economic value and breadth of the indirect economic value) throughout three stages of customer journey.Design/methodology/approachThis study collected data from the Internet-shopping platforms, namely Taobao and T-Mall from 2019 to 2020 with particular focus on three product categories: lipstick (fast-moving consumer goods), mobile phones (durable goods) and alcohol (a hybrid of the other two product types) from 37 selected firms. The CVSM employs an entropy-based multiple criteria analysis, of which the weight of each indictor is not fixed artificially, but computed by the entropy-based method that calculates informative differences among the indicators (profit, revenue, positive reviews, search index and likes and favorites).FindingsThe result shows that product categories and market status have a moderation effect on three components in customer values. The findings suggested marketing strategies for different consumer goods, where the fast-moving consumer goods like lipstick should focus on the pre-purchase stage while the durable goods should emphasize post-purchase stage when the market is rapidly changing.Originality/valueThe study brings new insights to Kumar’s customer value theory by integrating product categories and the market status, revealing that three components of customer values differ in their contributions to the whole customer values. This paper further contributed managerial suggestions for marketers with regards to three stages of customer journey.
Journal Article
The influence of trust and relationship commitment to vloggers on viewers' purchase intention
PurposeThis study extends the commitment-trust theory from the perspective of relationship marketing and explores its effect on purchase intention under the moderation of trust by investigating vloggers' relationship marketing in the context of social media.Design/methodology/approachThe study employs a survey investigation with online questionnaires in China, and the hypotheses were tested using multiple regression analyses, with 319 valid consumer responses.FindingsThe findings reveal that the extended commitment-trust theory is applicable in the context of social media. Perceived relationship commitment, expertise, physical attractiveness, social attractiveness and self-disclosure play a significant role in predicting purchase intention. Relationship commitment proves to be a mediator between the antecedents and purchase intention. Trust shows a moderating effect on the antecedents and relationship commitment.Originality/valueThe study provides evidence of the importance of the above-mentioned antecedents in influencing viewers' relationship commitment to vloggers in the context of social media. The results contribute to the development of the commitment-trust theory and an understanding of the theory's underlying mechanisms. The result also provides further evidence of the effect of trust on relationship commitment.
Journal Article
Corporate financial distress diagnosis model and application in credit rating for listing firms in China
With the enforcement of the removal system for distressed firms and the new Bankruptcy Law in China's securities market in June 2007, the development of the bankruptcy process for firms in China is expected to create a huge impact. Therefore, identification of potential corporate distress and offering early warnings to investors, analysts, and regulators has become important. There are very distinct differences, in accounting procedures and quality of financial documents, between firms in China and those in the western world. Therefore, it may not be practical to directly apply those models or methodologies developed elsewhere to support identification of such potential distressed situations. Moreover, localized models are commonly superior to ones imported from other environments.
Based on the Z-score, we have developed a model called Z China score to support identification of potential distress firms in China. Our four-variable model is similar to the Z\"-score four-variable version, Emerging Market Scoring Model, developed in 1995. We found that our model was robust with a high accuracy. Our model has forecasting range of up to three years with 80 percent accuracy for those firms categorized as special treatment (ST); ST indicates that they are problematic firms. Applications of our model to determine a Chinese firm's Credit Rating Equivalent are also demonstrated.
Journal Article
Electronic disclosure and financial knowledge management
In this paper, we reported the benefits of using eXtended Markup Language (XML) to support financial knowledge management and discussed number of issues associated with developing an XML-based financial knowledge management system. Current searching engines do not provide sufficient performance in terms of recall, precision, and extensibility for financial knowledge management, because the data represented in HTML format cannot support financial knowledge management effectively. On the other hand, XML provides a vendor-neutral approach to structure and organize contents as XML authors are allowed to create arbitrary tags to describe the format or structure of data. A prototype of XML-based ELectronic Financial Filing System (ELFFS-XML) is developed, and value-added services such as automatic tag generation and cross-linking related information from different data sources are provided to enable knowledge representation and knowledge generation. We compared the XML-based ELFFS with the original HTML-based ELFFS and SEDAR — an electronic filing system used in Canada, and we found that ELFFS-XML is able to provide much more functionalities to support knowledge management. We also compared our automatic tag generation result with the experts’ and investors’ choices, and recommended some directions for future development of similar electronic filing systems.
Journal Article
A Model of Stock Manipulation Ramping Tricks
Ramping tricks of trade-based stock manipulation have evolved greatly in the fight with stricter market regulation, and can be extremely complicated nowadays. Despite the rigidity and soundness, theoretical models proposed in extant literature can hardly be applied directly to real market data, due to their assumptions being far away from reality. On the other hand, empirical studies of ramping manipulation still lack guidance and support from theories that can better reflect ramping details in practice. This paper addresses this gap by constructing a theoretical model that is closely linked to practical detection, in the framework of behavioral finance. New insights into concrete ramping manipulation tricks are also contributed to the literature. The potential of the model for manipulation detection is demonstrated by applying it to the two most infamous manipulation cases in the history of Chinese stock market.
Journal Article