Notice Board :

Call for Paper
Vol. 16 Issue 2

Submission Start Date:
Feb 01, 2024

Acceptence Notification Start:
Feb 10, 2024

Submission End:
Feb 25, 2024

Final MenuScript Due:
Feb 28, 2024

Publication Date:
Feb 28, 2024
                         Notice Board: Call for PaperVol. 16 Issue 2      Submission Start Date: Feb 01, 2024      Acceptence Notification Start: Feb 10, 2024      Submission End: Feb 25, 2024      Final MenuScript Due: Feb 28, 2024      Publication Date: Feb 28, 2024




Volume XIV Issue XI

Author Name
Kishan kumar, Chetan Agrawal, Prachi Tiwari
Year Of Publication
2022
Volume and Issue
Volume 14 Issue 11
Abstract
The rapid expansion of credit card use in today's society makes security a top issue all the time. Increased credit card use also results in an increase in credit card scams, such as the theft of money from credit cards and online money speculation, among other things. Therefore, in order to overcome this problem, businesses invest a great deal of money and time into finding these con artists or other unauthorized users. In this study, we will discuss the classification methods that may be applied to credit card datasets to identify credit card fraud. Fraud avoidance and fraud discovery systems are the two main ways to prevent frauds and the losses brought on by fraud. Fraud prevention is a realistic strategy used to reduce the frequency of fraud. When criminals go beyond the fraud prevention plan and start a fraudulent transaction, fraud discovery systems become relevant. The acceptance of the prevention mechanism by a fraudulent transaction is impossible to discern. Therefore, the go
PaperID
2022/EUSRM/11/2022/61356

Author Name
Pradeep Bhawsar, Sumit Sharma
Year Of Publication
2022
Volume and Issue
Volume 14 Issue 11
Abstract
Nowadays, social media sites like Facebook, Instagram, and LinkedIn connect different people, creating an unofficial community map. Differentiating networks in current web-based media charts is a crucial task. The informal organization may be divided into several groups of hubs that have the same behaviors since networks allow us to collect clients that exhibit similar behaviors. This information on people groups can help us focus key information on customers in a specific geographic area and help us make critical decisions. Researchers and experts from various fields have been working to discover a solution to this issue in recent years using a range of different approaches and methodologies. The study project that was suggested has led to an extensive and thorough review of different ways that have been used to address the issue of finding new local areas. By grouping the aforementioned collection of strategies into four different categories—framework factorization, irregular walk, p
PaperID
2022/EUSRM/12/2022/61349

Author Name
Mahalya Chopra, Gajendra Singh
Year Of Publication
2022
Volume and Issue
Volume 14 Issue 11
Abstract
The ability to predict student performance is crucial in understanding the student succession rate. Education is the Power, and by forecasting educational success using the right metrics, we will be able to address student weakness at the appropriate moment by utilising accurate pedagogies and techniques. Various machine learning technologies, including supervised, unsupervised, and reinforcement learning, have been created to predict student performance. Using historical observations, machine learning enables us to learn and generate accurate predictions. In this study, we give a literature review on the topic of predicting student achievement using machine learning techniques, along with the benefits and drawbacks of various machine learning approaches
PaperID
2022/EUSRM/11/2022/61339