Online Transaction Fraud Detection using Backlogging on E-Commerce Website

  • : Ms Word, Ms Word Format
  • : 70 Pages
  • : ₦5,000
  • : 1-5 Chapters
  •  
  • Click to DOWNLOAD Materials

Online Transaction Fraud Detection using Backlogging on E-Commerce Website

 

ABSTRACT

We here come up with a system to develop a website which has capability to restrict and block the transaction performing by attacker from genuine user’s credit card details. The system here is developed for the transactions higher than the customer’s current transaction limit. We tried to detect fraudulent transaction before transaction succeed. During registration we take required information which is efficient to detect fraudulent user activity. Here we present a Behavior and Location Analysis (BLA). The details of items purchased in Individual transactions are usually not known to any Fraud Detection System (FDS) running at the bank that issues credit cards to the cardholders. Hence, We implemented BLA for addressing this problem. An advantage to use BLA approach to reduce number of false positive transactions identified as malicious by an FDS although they are genuine. An FDS runs at a credit card issuing bank. Each incoming transaction is submitted to the FDS for verification. FDS receives the card details and transaction value to verify, whether the transaction is genuine or not. The types of goods that are bought in that transaction are not known to the FDS. Bank declines the transaction if FDS confirms the transaction to be fraud. User spending patterns and geographical location is used to verify the identity. If any unusual pattern is detected, the system requires re-verification. Based upon previous data of that user the system recognizes unusual patterns in the payment procedure. System will block the user after 3 invalid attempts.

CHAPTER ONE

 

INTRODUCTION

  • Background of study

Information mining involves the use of complicated information investigation instruments to discover previously obscure, substantial patterns and relationships among large informational indexes. These apparatuses can include mathematical calculations, factual models, and machine learning methods, (for example, Neural Networks or Decision Trees). Consequently, information mining comprises more than the collection and management of information, it likewise includes investigation and prediction. Information mining can be performed on information represented in textual, quantitative or multimedia structures. Information mining applications can use a range of parameters to observe the information. This includes an affiliation, characterization, sequence or way examination, clustering, and forecasting. When utilizing typical measures, detection of credit card fraud is a dubious errand. Therefore, the development of the credit card fraud detection model has become a lot of significant, whether in the academic, association, or business network recently. Proposed models or existing models are generally insights driven or Artificial Intelligent-based (AI), which have the theoretical advantages in not forcing counterfeit suspicions on the information variables.

Credit Cardholders have numerous beneficiary schemes to hold interest-free balances for just about two months with “grace-period”. Suitable data on fraudulent activities is strategic to the financial business. E commerce merchants have huge databases. The extraction of significant business data should be possible from these information stores. Datastores have some patterns into clusters that are normal to the information. The concept of fraud detection has been laid on information mining techniques which include affiliation rules, clustering, and order. The chief purpose of research on fraud detection has been focused on pattern coordinating in which irregular patterns are identified from the typical ones. The prevalence of online shopping is developing step by step on high pace. These days, Credit card is the most mainstream mode of payment (59 percent), Germany and Great Britain have the largest number of online shoppers. For the most part, Retailers like Wal-Mart handle a lot larger number of credit card transactions online just as regular purchases. There are numerous choices for taking care of credit card payments on the Internet, as the processing of credit card transactions is generally independent of the type of e-commerce exchange. While a huge segment of e-commerce would comprise of credit card purchases, like regular or often. It is more significant for businesses and associations that rely upon on income from e-commerce to realize the alternatives available just as costs linked with credit card transaction processing on the Internet. Nobody has any clue about the transaction being processed are whether a fraudulent transaction or legitimate which has passed the prevention mechanisms. Therefore, the objective of the fraud detection system is to pre-determine every transaction for the chance of being fraudulent regardless of the prevention mechanisms and to categorize transactions as fraudulent ones as early as possible after the fraudster has begun to submit a fraudulent transaction. Credit card fraud detection is a tremendous errand yet in addition trendy problem to solve. Numerous fraud detection systems estimate the transactions and generate a doubt score (generally a likelihood between 0 and 1) which demonstrates the chances of that transaction to be fraudulent. Computational procedures of these scores are applicable to the techniques used to construct the model(s) in the fraud detection systems. These corresponding scores are used with a predefined threshold value to differentiate between fraudulent transactions from the legitimate ones easily.

Presentation of new technologies, for example, telephone, automated teller machines (ATMs) and credit card systems have enlarged the measure of fraud misfortune for some E commerce merchants. Breaking down whether each transaction being processed is legitimate or not is very expensive is another undertaking to determine transaction genuinely. Further, on the off chance that we check them in all transactions and affirm whether a transaction was done by a client or a fraudster by calling all cardholders is cost- prohibitive. Fraud prevention via programmed fraud detections mechanism can be applied where the well-known arrangement methods can be identified, where pattern recognition systems have key capacities. One can learn from fraud that happened previously and categorize new transactions easily. Recently, perhaps the most frequently used technique is Neural Networks in the credit card business.

 

1.2      Statement of the problem

According to Addis fortune (2016) “Inefficiency in controlling direct costs and employee processing error, losses due to employee and customer theft and fraud, business interruptions from damage to assets, facilities, systems; transaction processing.” In response to computation in E commerce industry, E commerce merchants used different technologies, systems and methods, as well as employing competent experts, in order to keep their existent in the market. Even if they operate their business by coordinating technology and experts, they cannot stop the occurrence of fraudulent acts. The most common risks of fraud on the E commerce merchant operation is issuing of Cash Payment Order (CPO) without securing sufficient funds from customers, releasing import documents before receiving full funds, transferring funds out of dormant accounts, putting counterfeit signatures on special clearance forms by E commerce merchant messengers so that a customer account is credited, outright theft by tellers and approving None-Sufficient Fund (NSF) cheques, and using false identity.

 

As mentioned by Tom Keatinge, (2014), over the last years the emergence of private E commerce merchants and their expansions has increased rapidly, and the expansion of their services and new E commerce merchant products can be accompanied by an increase indifferent type of fraudulent acts. Therefore, controlling fraud is the first task in commerces.

This fraud committed by using other co-works user name and password by the E commerce merchant employees and employees collaborate with outsider customers. Currently there are rare studies related to fraud and its control in Nigeria. Based on this the purpose of this research is to assess fraud practices and the controlling mechanisms used by E store.

1.3      Research Questions

  1. Whether there is Anti-fraud Policy and controlling mechanism to protect the E commerce merchant from fraud?
  2. What types of Online transaction fraud are experienced in E store?
  3. How effective is backlogging in controlling fraud in E-commerce?
  4. What is the awareness of employee’s about fraud and its controlling mechanisms?

 

1.4      Objectives of the study

  1. to identify the existence of backlogging and other controlling mechanism to protect the E commerce merchant from fraud
  2. to find out the types of fraud experienced in the E store;
  3. to assess the effectiveness of the controlling system in commerce
  4. to evaluate the awareness of employees about fraud and its controlling

 

1.5      Definition of Terms

Internal control: “it is a process, affected by an entity’s board of directors, management and other  personnel,  designed  to  provide  reasonable  assurance regarding the achievement of objectives in the following categories: effectiveness and efficiency of operations, reliability  of  financial  reporting and compliance with applicable laws and regulations” (Draz 2011).

Fraud: according to (IPPF) (cited in ACL 2014)“fraud is any illegal act characterized by deceit, concealment, or violation of trust. These acts are not dependent upon the threat of violence or physical force. Frauds are perpetrated by parties and organizations to obtain money, property or services, to avoid payment or loss of services or to secure personal or business advantage”.

 

1.6      Significance of the study

The competition among E commerce merchants has become stiff these days to attract and retain customers. In order to do that E store needs to implement effective controlling mechanism to protect the customers and the E commerce merchant from frauds. The study will be significant to the E commerce sector in general, and specifically to E store in identifying the kinds of frauds that are encountered in their operations. The findings of the study are also significant in identifying the gaps in the existing controlling mechanisms, and can be useful in the pursuits of E commerce merchants toward reducing the rising cases of frauds in the E commerce sector. Finally, the study will also help as reference to other researchers who will be interested to conduct a research related to the subject matter.

1.7      Scope of the study

The scope of the study was delimited to employees of E store, Lagos Branches. Even though it is very important to cover all the area E commerce merchants across the country, due to the wide geographical dispersion of area E commerce merchants as well as time and money constraints upcountry branches were not included. The study included only area E commerce merchants based in Lagos. The study only focused on respondents from clerical, up to managerial level. Non clerical employees like security guards, cleaners or messengers are not included. Other data collection tools like focus group discussion would also have given more insight into this matter; but due to time and resource limitation only questionnaires were used as data collection tool on the study.

1.8      Organization of the Study

This study is organized in to five chapters. The first chapter presents the introduction which includes background of the study, background of the organization, statement of the problem, basic research questions, objective of the study, significance of the study, scope of the study. The second chapter shows the literature review while the third chapter contains brief description of the research design. The fourth chapter presents and analyzes the results. Finally, chapter five presents the conclusions and recommendation of the study.

Online Transaction Fraud Detection using Backlogging on E-Commerce Website

Sharing is caring!

Leave a Reply