Abstract— Dueto the advent of Internet technologies, Ecommerce widely adapted mode ofbusiness in modern times. Fraudulent activity exits in many areas of businessesand our daily life. Thousands of dollars are loss every day due to the fraud inpurchased items and immediately cancelled orders without any proper reason. Inexisting there is lot work in E-commerce fraud detection in credit card frauddetection, network intrusion etc. But limited work in E-commerce frauddetection for user orders behavior.
Now in this paper we are proposing aconcept of E-commerce fraud detection in user orders behavior. For this wecollect user’s orders, like purchased and cancelled data. For every user datawe will compare with email, mobile, IP address and address for eachtransactions. Based on that data we can effect to the users that hide the CODoption, and block the user account.
To design potent and efficient frauddetection concept is the key for reducing the losses in transactions Keywords-Fraud,E-Commerces. I.INTRODUCTION E-commercepayment systems have become popular due to widespread use of the internet-basedshopping and banking.
Rapid increment of this era billions of dollars are lostevery year due to credit card fraud. Fraud is an act of betrayal intended forpersonal usage or to harm a loss to someone. Fraudster only wants to know thepersonal information related to card (card number, card expiry date etc.). Itcan be possible physically or virtually. It is commonly understood asdishonesty to gain some advantage which is often financial, over anotherperson. The volume of electronictransactions has raised signi?cantly in last years, mainly due to the popularizationof electronic commerce (e-commerce), such as online retailers like Amazon,eBay, etc. We also observe a signi?cant increase in the number of fraud cases,resulting in billions of dollars losses each year worldwide.
Therefore, it isimportant and necessary to developed and apply techniques that can assist infraud detection and prevention, which motivates ourresearch. This project aims to apply and evaluate computational techniques toidentify fraud in electronic transactions. II. LITERATURE SURVEY Ghosh and Reilly 1 have proposed credit card frauddetection with a neural network.
They have built a detection system, which istrained on a large sample of labeled credit card account transactions. Thesetransactions contain example fraud cases due to lost cards, stolen cards,application fraud, counterfeit fraud, mail-order fraud, and non-received issue(NRI) fraud. Recently, Syeda et al. 2 have used parallel granular neuralnetworks (PGNNs) for improving the speed of data mining and knowledge discoveryprocess in credit card fraud detection. A complete system has been implementedfor this purpose. Stolfo et al. 3 suggest a credit card fraud detectionsystem (FDS) using meta learning techniques to learn models of fraudulentcredit card transactions.
Meta learning is a general strategy that provides ameans for combining and integrating a number of separately built classifiers ormodels. A meta classifier is thus trained on the correlation of the predictionsof the base classifiers. The same group has also worked on a cost-based modelfor fraud and intrusion detection. They use Java agents for Meta learning(JAM), which is a distributed data mining system for credit card frauddetection A number of important performance metrics like True Positive—FalsePositive (TP-FP) spread and accuracy have been defined by them. Alekerov et al.4 present CARDWATCH, a database mining system used for credit card frauddetection.
The system, based on a neural learning module, provides an interfaceto a variety of commercial databases. Kim and Kim 5 have identified skeweddistribution of data and mix of legitimate and fraudulent transactions as thetwo main reasons for the complexity of credit card fraud detection. Based onthis observation, they use fraud density of real transaction data as aconfidence value and generate the weighted fraud score to reduce the number ofmisdetections.
Fan et al. 6suggest the application of distributed data mining in credit card frauddetection. Brauset al. 7 have developed an approach that involves advanceddata mining techniques and neural network algorithms to obtain high fraudcoverage. Chiu and Tsai 8 have proposed Web services and data miningtechniques to establish a collaborative scheme for fraud detection in thebanking industry. With this scheme, participating banks share knowledge aboutthe fraud patterns in a heterogeneous and distributed environment. To establisha smooth channel of data exchange, Web services techniques such as XML, SOAP,and WSDL are used.
III. PROPOSED METHODOLOGY 1. Theunethical actions of the dishonest customers is becoming a major concern amongall the online sellers.2. Our proposed system thereby provides a practical solution to avoid the buyer fraud with the help ofhistory of their purchased and cancelled products.
· So for the first timeuser can’t get COD option, even though it is repeated for the second time also,account will block.· If any user is fraud,again he is trying to register with new account we will compare with email,mobile, IP address and address. If it is matched he won’t get COD.· And seller has oneproposed option that if he block any user application won’t get give thatseller products to that user Fig. ArchitecturalDesign IV.
CONCLUSIONSFor the fraud detection ine-commerce various approaches are there. In this paper, we have reviewed someof the detection approaches. Each approach having its own rule sets toimplement and rules are not clearly described in approach.
Based on observationtable we can conclude that Hybridization of BLAST-SSAHA approach is bestsuitable for the fraud detection in terms of cost and accuracy. To detect afraud is necessity but also to decrease false alarm is also necessary.BLAST-SSAHA?s True positive (TP) ratio having less than Dempster Shafer theoryand Fuzzy Darwinian detection but cost of both approaches is quite expensive.So it would not beneficial to implement both together.
So by implementing ruleswhich are used in another approach or implementing advanced rule sets into theBLAST-SSAHA. So there is possibility to increase True Positive result anddecrease false alarm. V.ACKNOWLEDGMENT It gives us great pleasure inpresenting this project report titled “Online blood Connect” and we wish toexpress our immense gratitude to the people who provided invaluable knowledgeand support in the completion of this project. Their guidance and motivationhas helped in making this project a great success. We express our gratitude toour project guide Ass.prof.B.
Pravallika, who provided us with all the guidance andencouragement throughout the project development. We would also like to express our sinceregratitude to the respective Project Incharge Ass.prof.
k.Lakshmi Narayanamma forproviding us the needed assistance, detailed suggestions and also encouragementto do the project.. We are eager and glad to express our gratitude to the Headof the Information Technology Dept. Prof. Dr .K. Srinivasa Reddy, for hisapproval of this project.
We would like to deeply express our sincere gratitudeto our respected principal Prof. Dr.L.
V.N.Prasad and the management ofInstitute of Aeronautical Engineering for providing such an ideal atmosphere tobuild up this project with well-equipped library with all the utmost necessary reference materials and up to dateIT Laboratories. We are extremely thankful to all staff and the management ofthe college for providing us all the facilities and resources required.