Search results

The purpose of this paper is to compare nine different models to evaluate consumer credit risk, which are the following: Logistic Regression (LR), Naive Bayes (NB), Linear Discriminant Analysis (LDA), k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), Classification and Regression Tree (CART), Artificial Neural Network (ANN), Random Forest (RF) and Gradient Boosting Decision Tree (GBDT) in Peer-to-Peer (P2P) Lending.

The author uses data from P2P Lending Club (LC) to assess the efficiency of a variety of classification models across different economic scenarios and to compare the ranking results of credit risk models in P2P lending through three families of evaluation metrics.

The results from this research indicate that the risk classification models in the 2013–2019 economic period show greater measurement efficiency than for the difficult 2007–2012 period. Besides, the results of ranking models for predicting default risk show that GBDT is the best model for most of the metrics or metric families included in the study. The findings of this study also support the results of Tsai et al. (2014) and Teplý and Polena (2019) that LR, ANN and LDA models classify loan applications quite stably and accurately, while CART, k-NN and NB show the worst performance when predicting borrower default risk on P2P loan data.

The main contributions of the research to the empirical literature review include: comparing nine prediction models of consumer loan application risk through statistical and machine learning algorithms evaluated by the performance measures according to three separate families of metrics (threshold, ranking and probabilistic metrics) that are consistent with the existing data characteristics of the LC lending platform through two periods of reviewing the current economic situation and platform development.

In the current era of technological advancement, the architectural, engineering and construction (AEC) industry is undergoing a radical transformation, prompting researchers to explore new breakthroughs that can revolutionise the construction process. This paper delves into the use of cutting-edge technologies such as building information management (BIM), blockchain and the Internet of Things (IoT), along with advanced management techniques such as work breakdown structure (WBS) and Agile thinking, to enhance the industry’s efficiency, productivity, quality and cost-effectiveness. Moreover, the pressing need for a sustainable, secure and transparent sector amplifies the significance of the proposed research.

This study’s research approach comprises an intensive literature review to construct a conceptual framework, followed by an exploratory questionnaire to validate the framework.

This paper demonstrates how blockchain combined with a WBS and a BIM platform may boost collaboration in order to experience efficient and trusted workflow scenarios that can overcome many of the challenges given in a traditional building technique. The research findings emphasise the benefits of the proposed new mentality approach, which incorporates all of the previously described tools/techniques to the business.

This paper highlights the advantages of leveraging a combination of blockchain, WBS and BIM platforms to boost collaboration and enable efficient and trustworthy workflow scenarios that can surmount the difficulties inherent in traditional AEC industry collaboration methods.

This study provides original insights into the challenges and opportunities of using blockchain for AEC collaboration, by exploring the potential of decentralised blockchain networks to improve the security, efficiency and transparency of collaborative data sharing and management.

This paper aims to explore the impacts of a blockchain network implementation to support purchasing processes of a Brazilian public organization.

The Grumbach method was used to build the scenarios. Five experts with knowledge in blockchain and experience in public procurement were consulted on 20 possible preliminary events, defining their probability of occurrence and relevance. The data obtained were processed in Puma software, which returned a selection of ten definitive events, based on probability, relevance and standard deviation indicators, generating a map of prospective scenarios.

Three following scenarios are shown, the ideal scenario, the one with greater implantation benefits and fewer complications; the trend scenario, more likely to occur under current conditions; and the most likely scenario of occurrence, according to experts. The results indicated which simulated events are drivers (motives), and which are influenced (dependent). They were categorized as opportunities or threats to the deployment of the technology.

Although public procurement processes are standardized by Brazilian legislation, new events may arise from the replication of the model in different organizations. The research revealed the need for practical testing in a simulated public procurement environment.

The article explores the interaction between disruptive network technology and processes linked to public sector efficiency. Studies on electronic government point to the future of public management.