Combating emerging financial risks in the big data era: A perspective review

Cheng, Xueqi; Liu, Shenghua; Sun, Xiaoqian; Wang, Zidong; Zhou, Han; Shao, Yu; Shen, Huawei

doi:10.1016/j.fmre.2021.08.017

Cited by 57 publications

(15 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The social network is one of the favorite means to perform social interactions and exchange information. Link prediction is a crucial task in social network analysis to infer the potential links between nodes, and can be applied in scenarios like IoT network analysis [19,20], criminal network analysis [21], fraud detection [6,7]. The objective of link prediction in the social network can be divided into two categories: find missing interactions in static graphs and predict future interactions in dynamic graphs [22].…”

Section: Link Prediction In Social Networkmentioning

confidence: 99%

“…For instance, inferring the missing interactions with infections for teasing out the potential transmission chain of the virus can contribute to the control of outbreaks of COVID-19. Another practical application in fraud investigation [ 6 , 7 ] is inferring the hidden trading behaviors of fraudsters to restore money transferring chains in financial transaction networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

NEAWalk: Inferring missing social interactions via topological-temporal embeddings of social groups

Shen

Jiang

et al. 2022

Knowl Inf Syst

Self Cite

View full text Add to dashboard Cite

Real-world network data consisting of social interactions can be incomplete due to deliberately erased or unsuccessful data collection, which cause the misleading of social interaction analysis for many various time-aware applications. Naturally, the link prediction task has drawn much research interest to predict the missing edges in the incomplete social network. However, existing studies of link prediction cannot effectively capture the entangling topological and temporal dynamics already residing in the social network, thus cannot effectively reasoning the missing interactions in dynamic networks. In this paper, we propose the NEAWalk, a novel model to infer the missing social interaction based on topological-temporal features of patterns in the social group. NEAWalk samples the query-relevant walks containing both the historical and evolving information by focusing on the temporal constraint and designs a dual-view anonymization procedure for extracting both topological and temporal features from the collected walks to conduct the inference. Two-track experiments on several well-known network datasets demonstrate that the NEAWalk stably achieves superior performance against several state-of-the-art baseline methods.

show abstract

Section: Link Prediction In Social Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

NEAWalk: Inferring missing social interactions via topological-temporal embeddings of social groups

Shen

Jiang

et al. 2022

Knowl Inf Syst

Self Cite

View full text Add to dashboard Cite

show abstract

“…Today and in the future, humans need strategies to manage information and data with various media and networks [16]. Various data management approaches increase innovative value and profitability in business and other strategic areas [17]. Data with various categories can be integrated to explore knowledge and support the latest research on a small scale and a large scale [18].…”

Section: Introductionmentioning

confidence: 99%

Prediction of linear model on stunting prevalence with machine learning approach

Mambang

Marleny²,

Zulfadhilah³

2023

Bulletin EEI

View full text Add to dashboard Cite

An increase in the number of residents should be anticipated including in the health sector, especially the problem of stunting. Stunting in children disrupts height and lack of absorption of nutrients. Information and data drive change in many areas such as health, entertainment, economics, business, and other strategic areas. The stages carried out in this study are initiating, developing linear models, and making prediction results on linear machine learning models. The results of testing with the scikit-learn linear model with a minimum variable of 19 get the best test results, namely the polynomial regression with pipeline model with mean absolute percentage error (MAPE) 0.02, root mean square error (RMSE) 3.32, and coefficient of determination (R2) 1,00. Testing with the scikit-learn linear model with a maximum variable of 48 gets the best test results, namely the polynomial regression with pipeline model with MAPE 0.00, RMSE 3.79 and R2 1.00. Testing with the scikit-learn linear model with an average variable of 32 gets the best test results, namely the polynomial regression model with MAPE 0.01, RMSE 3.32, and R2 1.00. The results of testing with the scikit-learn linear model with the minimum, maximum, and average variables get the best test results, namely the polynomial regression with pipeline model.

show abstract

“…The application of media attention to financial markets are growing with the outbreak of the internet and big data [14]. Most of these application focus on combating the potential financial risk, including four major types of risk, i.e., Liquidity risk, credit risk, market risk, and systematic risk [8]. Risk during operation of financial institutions receives less attention despite of the close connection to the all types of risk above.…”

Section: Introductionmentioning

confidence: 99%

Empirical Study of the Connection of Media Attention and Bank's Operating Risk in United States

Tan¹,

Zhang²

2022

Proceedings of the 2022 2nd International Conference on Computer Technology and Media Convergence Design (CTMCD 2022)

View full text Add to dashboard Cite

Public opinions were proved to have effects on the financial risk. According to the previous theoretical explanations about the impact of polarized opinions on financial market, media attentions, as one of the primary representative indexes in public opinions, was assumed to be associated with financial risk by gathering warning information from various channels in markets. By introducing data of GDELT from Google, media attention was quantified as the frequency of reports containing certain keyword. The operational risk of U.S. banks was quantified by NPLs as used in numerous previous studies. Various regression models were set for analyzing the connection of media attention to the operational risk under a group of controlled macroeconomic parameters. Robust results were obtained from the above estimations supporting the early assumption on connecting media attentions to risk. In addition, the outcomes of the above quantitative analysis displayed the heterogeneous effects of media attention on risk of banks with different asserts.

show abstract

Combating emerging financial risks in the big data era: A perspective review

Cited by 57 publications

References 45 publications

NEAWalk: Inferring missing social interactions via topological-temporal embeddings of social groups

NEAWalk: Inferring missing social interactions via topological-temporal embeddings of social groups

Prediction of linear model on stunting prevalence with machine learning approach

Empirical Study of the Connection of Media Attention and Bank's Operating Risk in United States

Contact Info

Product

Resources

About