Shu Takahashi, Kento Yamamoto, Shumpei Kobayashi, Ryoma Kondo, Ryohei Hisano
{"title":"银行转账网络中的动态链接和流量预测","authors":"Shu Takahashi, Kento Yamamoto, Shumpei Kobayashi, Ryoma Kondo, Ryohei Hisano","doi":"arxiv-2409.08718","DOIUrl":null,"url":null,"abstract":"The prediction of both the existence and weight of network links at future\ntime points is essential as complex networks evolve over time. Traditional\nmethods, such as vector autoregression and factor models, have been applied to\nsmall, dense networks, but become computationally impractical for large-scale,\nsparse, and complex networks. Some machine learning models address dynamic link\nprediction, but few address the simultaneous prediction of both link presence\nand weight. Therefore, we introduce a novel model that dynamically predicts\nlink presence and weight by dividing the task into two sub-tasks: predicting\nremittance ratios and forecasting the total remittance volume. We use a\nself-attention mechanism that combines temporal-topological neighborhood\nfeatures to predict remittance ratios and use a separate model to forecast the\ntotal remittance volume. We achieve the final prediction by multiplying the\noutputs of these models. We validated our approach using two real-world\ndatasets: a cryptocurrency network and bank transfer network.","PeriodicalId":501273,"journal":{"name":"arXiv - ECON - General Economics","volume":"6 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Dynamic Link and Flow Prediction in Bank Transfer Networks\",\"authors\":\"Shu Takahashi, Kento Yamamoto, Shumpei Kobayashi, Ryoma Kondo, Ryohei Hisano\",\"doi\":\"arxiv-2409.08718\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The prediction of both the existence and weight of network links at future\\ntime points is essential as complex networks evolve over time. Traditional\\nmethods, such as vector autoregression and factor models, have been applied to\\nsmall, dense networks, but become computationally impractical for large-scale,\\nsparse, and complex networks. Some machine learning models address dynamic link\\nprediction, but few address the simultaneous prediction of both link presence\\nand weight. Therefore, we introduce a novel model that dynamically predicts\\nlink presence and weight by dividing the task into two sub-tasks: predicting\\nremittance ratios and forecasting the total remittance volume. We use a\\nself-attention mechanism that combines temporal-topological neighborhood\\nfeatures to predict remittance ratios and use a separate model to forecast the\\ntotal remittance volume. We achieve the final prediction by multiplying the\\noutputs of these models. We validated our approach using two real-world\\ndatasets: a cryptocurrency network and bank transfer network.\",\"PeriodicalId\":501273,\"journal\":{\"name\":\"arXiv - ECON - General Economics\",\"volume\":\"6 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - ECON - General Economics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.08718\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - ECON - General Economics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08718","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Dynamic Link and Flow Prediction in Bank Transfer Networks
The prediction of both the existence and weight of network links at future
time points is essential as complex networks evolve over time. Traditional
methods, such as vector autoregression and factor models, have been applied to
small, dense networks, but become computationally impractical for large-scale,
sparse, and complex networks. Some machine learning models address dynamic link
prediction, but few address the simultaneous prediction of both link presence
and weight. Therefore, we introduce a novel model that dynamically predicts
link presence and weight by dividing the task into two sub-tasks: predicting
remittance ratios and forecasting the total remittance volume. We use a
self-attention mechanism that combines temporal-topological neighborhood
features to predict remittance ratios and use a separate model to forecast the
total remittance volume. We achieve the final prediction by multiplying the
outputs of these models. We validated our approach using two real-world
datasets: a cryptocurrency network and bank transfer network.