Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665700
Joseph R. Barr, Peter Shaw
The state of the art of data engineering and statistical algorithms opens the possibility for automating certain tasks Although field types of columns may not be known in advance, we assume data type is enforced, e.g., that date fields have nothing but dates, in some specific format. Data related tasks include feature engineering, data processing, text recognition and errors detection. For example, of interest to auditors is detection of input errors in financial spreadsheets, fraudulent transactions, abusive insurance claims, etc. Clearly, for a large dataset, an auditor cannot possibly go through the entire set of records, so a way to highlight records of interest may be of great value by increasing audits productivity. Once an auditor has identified a suspect record, he/she may be interested to give “similar” record a closer examination. In this short essay we demonstrate the plausibility of automating the process of feature creation, outlier detection and calculating the distance between any two records in a spreadsheets whereby providing the proverbial auditor the means to quickly identify strange and unusual records.
{"title":"AI Application to Data Analysis, Automatic File Processing","authors":"Joseph R. Barr, Peter Shaw","doi":"10.1109/AI4I.2018.8665700","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665700","url":null,"abstract":"The state of the art of data engineering and statistical algorithms opens the possibility for automating certain tasks Although field types of columns may not be known in advance, we assume data type is enforced, e.g., that date fields have nothing but dates, in some specific format. Data related tasks include feature engineering, data processing, text recognition and errors detection. For example, of interest to auditors is detection of input errors in financial spreadsheets, fraudulent transactions, abusive insurance claims, etc. Clearly, for a large dataset, an auditor cannot possibly go through the entire set of records, so a way to highlight records of interest may be of great value by increasing audits productivity. Once an auditor has identified a suspect record, he/she may be interested to give “similar” record a closer examination. In this short essay we demonstrate the plausibility of automating the process of feature creation, outlier detection and calculating the distance between any two records in a spreadsheets whereby providing the proverbial auditor the means to quickly identify strange and unusual records.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116531918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-09-01DOI: 10.1109/ai4i.2018.8665679
{"title":"Message from the Ai4i 2018 General Co-Chairs","authors":"","doi":"10.1109/ai4i.2018.8665679","DOIUrl":"https://doi.org/10.1109/ai4i.2018.8665679","url":null,"abstract":"","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125410283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：