Literature review: Anomaly detection approaches on digital business financial systems

Pinto, Sarah Oliveira; Sobreiro, Vinícius Amorim

doi:10.1016/j.digbus.2022.100038

Cited by 10 publications

(4 citation statements)

References 168 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies have validated that the roles and responsibilities of accounting professionals have transformed due to digitalization, and digital accounting offers probable benefits and drawbacks. It is also confirmed that the efficiency and accuracy of fraud detection can be improved by implementing it (Pinto & Sobreiro, 2022; Roszkowska, 2020) [41,49] . Digital accounting has substantially impacted the accounting profession (Rindasu, 2017) [48] .…”

Section: Review Of Literaturementioning

confidence: 81%

“…The second highest score (52) is for "Khatabook" and "Book Keeper-GST Invoice Billing Inventory," which is the next preference of users. "Xero Accounting" scored lowest (41), meaning it does not fulfill the users' requirements. "Zoho Books-GST Accounting," despite being costly, provides good and additional features and meets the users' needs because most of its other features received a 4-rating score.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating the effectiveness of digital accounting applications for small and medium enterprises: A user-centric approach

Sarawagi,

Gupta,

Singh

et al. 2024

Asian J. Manage. Commerce

View full text Add to dashboard Cite

Small and Medium Enterprises rely on digital accounting applications to manage their financial operations and remain competitive in their particular industries. These applications are available in numerous forms with diverse features, from free to paid versions. However, whether these applications genuinely suit their users' needs remain ambiguous. The study aims to evaluate the effectiveness of these applications by assessing user ratings and reviews or feedback. The study evaluates ten popular digital accounting applications from the Play Store of Android-based mobile devices and other online platforms, providing reviews and feedback on these applications. The study's findings indicate that "myBillBook" is ideal for accounting needs, with high user ratings and positive feedback. Another top contender is "Zoho Books-GST Accounting," known for its excellent features, albeit at a higher cost for the paid version, while "Xero Accounting" lags due to user dissatisfaction.

show abstract

Section: Review Of Literaturementioning

confidence: 81%

Section: Resultsmentioning

confidence: 99%

Evaluating the effectiveness of digital accounting applications for small and medium enterprises: A user-centric approach

Sarawagi,

Gupta,

Singh

et al. 2024

Asian J. Manage. Commerce

View full text Add to dashboard Cite

show abstract

“…M. R. Fernandes , V. R. Q. Leithardt , Senior Member, IEEE, and J. F. P. Santana A survey was carried out to verify the most cited ones for detecting novelties. Systematic reviews were analyzed on the application of Novelty Detection algorithms in different contexts, such as Business Financial Systems [15], IoT Environment [16], Prevention and Fighting against web attacks [17], and IoMT (Internet of Medical Things) [18]. In addition to these works, research correlated to this work was analyzed.…”

Section: Novelty Detection Algorithms To Help Identify Abnormal Activ...mentioning

confidence: 99%

Novelty detection algorithms to help identify abnormal activities in the daily lives of elderly people

Fernandes,

Leithardt,

Santana

2024

IEEE Latin Am. Trans.

View full text Add to dashboard Cite

In old age, several common health conditions, chronic illnesses, and disabilities affect the individual's physical and mental health and prevent him from carrying out Activities of Daily Living. In this context, this article presents a comparative study between some Machine Learning algorithms used to identify behavioral abnormalities based on ADL (Activities of Daily Living), through the Novelty Detection technique. ADL data from eHealth Monitoring Open Data Project database were used to create a model that defines the baseline behavior of an elderly person, and new observations, to verify significant changes in behavior, are classified as outliers or abnormal. The Local Outlier Factor, One-class Support Vector Machine, Robust Covariance, and Isolation Forest algorithms were analyzed, and the Local Outlier Factor obtained the best result, reaching a precision and F1-Score of 96%. As elderly people can have completely different routines, the data from the dataset used are not generalizable, but specific to everyone. In this work, the issue of model retraining is not evaluated, however, a variation is recommended in the period of weeks necessary for model retraining. Despite the good performance obtained, it is necessary to consider reproducing the experiments with data from other databases, to improve the generalization of the proposed solution, as well as to carry out a more refined validation. It is also necessary to carry out experiments to evaluate whether the variation in the types of activities carried out throughout a day by an elderly person, as well as the inclusion of new activities in the elderly person's routine, can impact the performance of the proposed model. Link to graphical and video abstracts, and to code: https://latamt.ieeer9.org/index.php/transactions/article/view/8373

show abstract

“…Codes were used in a categorization framework developed by Pinto et al [31] to help organize the primary methods and body of knowledge in this area and to help spot areas where further study is warranted. The statistical results also revealed a few research gaps, the most important of which are a standardized database, experiments with data of varying dimensionality, and performance indicators for detection algorithms.…”

Section: Related Workmentioning

confidence: 99%

Predicting Fraud in Financial Payment Services through Optimized Hyper-Parameter-Tuned XGBoost Model

Dalal

Seth²,

Rădulescu

et al. 2022

Mathematics

View full text Add to dashboard Cite

Online transactions, medical services, financial transactions, and banking all have their share of fraudulent activity. The annual revenue generated by fraud exceeds $1 trillion. Even while fraud is dangerous for organizations, it may be uncovered with the help of intelligent solutions such as rules engines and machine learning. In this research, we introduce a unique hybrid technique for identifying financial payment fraud by combining nature-inspired-based Hyperparameter tuning with several supervised classifier models, as implemented in a modified version of the XGBoost Algorithm. At the outset, we split out a sample of the full financial payment dataset to use as a test set. We use 70% of the data for training and 30% for testing. Records that are known to be illegitimate or fraudulent are predicted, while those that raise suspicion are further investigated using a number of machine learning algorithms. The models are trained and validated using the 10-fold cross-validation technique. Several tests using a dataset of actual financial transactions are used to demonstrate the effectiveness of the proposed approach.

show abstract

Literature review: Anomaly detection approaches on digital business financial systems

Cited by 10 publications

References 168 publications

Evaluating the effectiveness of digital accounting applications for small and medium enterprises: A user-centric approach

Evaluating the effectiveness of digital accounting applications for small and medium enterprises: A user-centric approach

Novelty detection algorithms to help identify abnormal activities in the daily lives of elderly people

Predicting Fraud in Financial Payment Services through Optimized Hyper-Parameter-Tuned XGBoost Model

Contact Info

Product

Resources

About