{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T18:44:52Z","timestamp":1774982692723,"version":"3.50.1"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":18,"publisher":"Elsevier BV","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>\u200bAccurate recording of employee working hours is fundamental for workforce management, operational planning, and regulatory compliance. Despite the widespread adoption of digital time-tracking systems, timesheet records remain susceptible to irregularities that can distort labor metrics, productivity indicators, and cost estimations. This study proposes a domain-informed analytical framework for detecting, classifying, and interpreting anomalous entries in employee attendance data.The methodology integrates outlier detection with operational context in a structured workflow. First, six relative deviation features are engineered to capture directional differences between planned and recorded work and lunch periods, including start times, end times, and durations. These features are normalized to ensure comparability across heterogeneous shifts. Second, univariate Tukey\u2019s fences are applied to identify mild and extreme outliers for each deviation feature. Extreme outliers are interpreted as potential measurement errors, whereas mild outliers are classified according to domain-defined directional rules as either operationally acceptable or operationally detrimental deviations. Third, unauthorized deviations are analyzed using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to reveal recurring behavioral patterns within the multidimensional deviation space. Finally, employee-level behavioral risk is quantified through a normalized Severity Index based on the frequency of unauthorized deviations relative to attendance frequency, enabling both global ranking and temporal monitoring.Applied to 4,726 anonymized timesheet records, the proposed approach effectively distinguishes measurement errors, acceptable deviations, and operationally detrimental behaviors while revealing structured patterns of noncompliance. By integrating robust statistics with domain knowledge, it enables scalable attendance analytics and workforce governance.<\/jats:p>","DOI":"10.2139\/ssrn.6502093","type":"posted-content","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T17:43:07Z","timestamp":1774978987000},"source":"Crossref","is-referenced-by-count":0,"title":["Outlier Analysis in Personnel Attendance Timesheet Records"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5905-3106","authenticated-orcid":true,"given":"Gon\u00e7alo","family":"Duarte Nunes","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2460-8825","authenticated-orcid":true,"given":"Jo\u00e3o","family":"Pinto da Silva","sequence":"additional","affiliation":[]},{"given":"Leandro","family":"Magalh\u00e3es","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8414-5826","authenticated-orcid":true,"given":"Ricardo","family":"Sousa","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-47578-3","author":"C C Aggarwal","year":"2017","journal-title":"Outlier Analysis"},{"key":"ref2","article-title":"Outliers in Statistical Data","author":"V Barnett","year":"1980","journal-title":"Wiley Series in Probability and Mathematical Statistics Applied Probability and Statistics"},{"key":"ref3","article-title":"Anomaly detection: A survey","volume":"41","author":"V Chandola","year":"1980","journal-title":"ACM Comput. Surv"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1051\/matecconf\/201816401020","article-title":"Rfid and iot for attendance monitoring system","author":"Dedy Irawan","year":"2018","journal-title":"MATEC Web Conf. 164, 01020"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1109\/TII.2021.3090362","article-title":"Unusual insider behavior detection framework on enterprise resource planning systems using adversarial recurrent autoencoder","volume":"18","author":"J Dr","year":"2022","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/00401706.1969.10490657","article-title":"Procedures for Detecting Outlying Observations in Samples","volume":"11","author":"F E Grubbs","year":"1969","journal-title":"Technometrics"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1109\/NICS.2018.8606895","article-title":"A solution based on combination of rfid tags and facial recognition for monitoring systems","author":"V D Hoang","year":"2018","journal-title":"2018 5th NAFOSTED Conference on Information and Computer Science (NICS)"},{"key":"ref8","first-page":"1","article-title":"Towards proxy-attendance detection using a digital attendance system and machine learning","author":"T Karve","year":"2019","journal-title":"IEEE Pune Section International Conference (PuneCon)"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1109\/ICAIT47043.2019.8987263","article-title":"Iot based smart attendance monitoring system using rfid","author":"U Koppikar","year":"2019","journal-title":"2019 1st International Conference on Advances in Information Technology (ICAIT)"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21105\/joss.00205","article-title":"hdbscan: Hierarchical density based clustering","volume":"2","author":"L Mcinnes","year":"2017","journal-title":"Journal of Open Source Software"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1080\/10618600.2020.1807997","article-title":"Anomaly Detection in High-Dimensional Data","volume":"30","author":"P D Talagala","year":"2021","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"ref12","author":"J W Tukey","year":"1977","journal-title":"Exploratory Data Analysis"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1109\/ICIPCN63822.2024.00032","article-title":"Smart attendance management using a self-supervised learning approach","author":"D Vikram","year":"2024","journal-title":"2024 5th International Conference on Image Processing and Capsule Networks (ICIPCN)"},{"key":"ref14","article-title":"Detection and prediction of anomalous behaviors of enterprise's employees based on data-mining and optimization algorithm","volume":"14","author":"X Zhang","year":"2024","journal-title":"Scientific Reports"},{"key":"ref15","article-title":"His M.Sc. dissertation on whispered speech segmentation using deep learning received a distinction grade of 19\/20 and was awarded","journal-title":"Electrical and Computers Engineering -Telecommunications, Electronics, and Computers from the Faculty of Engineering -University of Porto (FEUP)"},{"key":"ref16","journal-title":"Jo\ufffdo Pinto da Silva holds a Master's degree in Integrated Electronics and Computer Engineering from FEUP. Currently, he is in the final stages of completing his Ph.D. program in Electrical and Computer Engineering at FEUP, focusing on signal processing and Deep Learning techniques applied to whispered speech signals. Since 2021, he has been working at LIAAD, INESC TEC, in the field of Data Science and Machine Learning applied to industry. Additionally, he supervises master's dissertations in Machine Learning and Signal Processing"},{"key":"ref17","journal-title":"In the same year, he joined Valuedate as a Development Engineer, where he has taken on roles such as Product Owner and Senior Data Engineer. His work focuses on building scalable data pipelines and web applications using technologies such as Python, Django, AWS, Azure, and Heroku. Additionally, he contributes to team leadership, Agile development practices, CI\/CD workflows, JIRA, and DevOps. His responsibilities also include overseeing batch processing, ensuring data governance, managing production releases"},{"key":"ref18","year":"2004","journal-title":"He is currently a senior researcher and project manager at the Laboratory of Artificial Intelligence and Decision Support (LIAAD) at INESC TEC, with more than a decade of experience. At the same time, he is an assistant professor at the Faculty of Sciences of the University of Porto, where he teaches courses in programming, web applications, and databases. His work extends beyond academia into industry, where he coordinates national and international collaborative scientific projects in areas such as Machine Learning and Data Mining, predictive maintenance and quality, process mining, time series, signal processing, and forecasting. He has also supervised numerous master"}],"container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T17:45:36Z","timestamp":1774979136000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=6502093"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":18,"URL":"https:\/\/doi.org\/10.2139\/ssrn.6502093","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}