Research Article
Design and Application of a Credit Bank Based on Blockchain Technology
Issue:
Volume 9, Issue 1, March 2024
Pages:
1-8
Received:
7 March 2024
Accepted:
1 April 2024
Published:
17 April 2024
Abstract: Credit banks are an important way to build a lifelong learning system and a learning society. At present, various types of credit banks in China generally have limitations such as low efficiency in learning achievement certification and conversion, difficulty in ensuring the quality of learning achievement certification, and vague identification of credit banks. Blockchain technology has the characteristics of openness, consensus, transparent transactions, anonymity, tamper resistance, and traceability, which can effectively solve the centralized governance problems faced by the current construction of credit banks. This article elaborates on the current development status and characteristics of credit banks at home and abroad, analyzes the feasibility of combining credit banks with blockchain, and designs a blockchain based credit bank system architecture and processing flow to address the challenges of inconsistent credit conversion standards, low conversion efficiency, and data security risks in traditional credit banks. It proposes using block structure design to achieve secure and tamper proof credit data, proposes a smart contract based credit recognition and conversion method to achieve decentralized governance of credit banks, and establishes a blockchain based credit bank certification, conversion, and other application design models, which can provide technical support for the large-scale application of credit banks in the future.
Abstract: Credit banks are an important way to build a lifelong learning system and a learning society. At present, various types of credit banks in China generally have limitations such as low efficiency in learning achievement certification and conversion, difficulty in ensuring the quality of learning achievement certification, and vague identification of...
Show More
Research Article
The LSTM-EMPG Model for Next Basket Recommendation in E-commerce
Issue:
Volume 9, Issue 1, March 2024
Pages:
9-23
Received:
6 June 2024
Accepted:
4 July 2024
Published:
15 July 2024
DOI:
10.11648/j.ijics.20240901.12
Downloads:
Views:
Abstract: Personalized recommendations play a crucial role in the modern e-commerce landscape, enabling businesses to meet customers' evolving preferences and boost sales. As customer preferences change, businesses are realizing the importance of suggesting what customers might want to buy next. However, existing approaches face challenges in capturing sequential patterns in user behavior and accurately utilizing previous purchase information. These challenges can be addressed using Long Short-Term Memory Networks (LSTMs). Nevertheless, LSTMs alone may not fully capture users' repetitive purchase behavior or consider the exact timing of purchases. To account for these limitations, Probabilistic Models such as the Modified Poisson Gamma model (MPG) can be employed. The research reported in this paper proposes and investigates a new approach for the next basket recommendation based on the integration of LSTM with an enhanced Modified Poisson Gamma model to enhance next basket recommendation accuracy in e-commerce. The enhanced model (EMPG) includes a refinement of the MPG model to increase its predictive accuracy, and its recommendations are then integrated with an LSTM network to optimize the LSTM’s predictions. The proposed hybrid LSTM-EMPG model has been evaluated on the Instacart dataset and has produced superior results compared to the Multi-period LSTM, the GRU-based model. DREAM (RNN), and DREAM (LSTM) in terms of predictive accuracy, achieving a higher precision and recall.
Abstract: Personalized recommendations play a crucial role in the modern e-commerce landscape, enabling businesses to meet customers' evolving preferences and boost sales. As customer preferences change, businesses are realizing the importance of suggesting what customers might want to buy next. However, existing approaches face challenges in capturing seque...
Show More
,
Gerard Thomas McKee
