Academic Journals Database
Disseminating quality controlled scientific knowledge


Author(s): Ajith Medukonduru | Manjula Patil

Journal: International Journal of Computer & Electronics Research
ISSN 2320-9348

Volume: 2;
Issue: 3;
Start page: 199;
Date: 2013;
Original page

Keywords: World Wide Web | Online Shopping | Fraud Detection | Online Probit Model | Auction

Electronic commerce has become more and more accepted from the time when the World Wide Web has emerged. Numerous websites permit Internet users to purchase and put on the market products and services online, which benefits everybody in terms of expediency and profitability.   The conventional online shopping business permit sellers to put up for sale a product or service at a predetermined price, where buyers can decide to obtain if they find it to be a good agreement. Comparable to any platform supporting financial connections, online auction be a focus for criminals to perform fraud. Due to the advantages from online trading, schemers are taking benefits to attain misleading activities against truthful parties to get hold of deceptive earnings. Application of Proactive fraud-detection moderation systems is usually functional to distinguish and avert such prohibited and deceptive activities in a most important Asian online auction site, where hundreds of thousands of novel auction cases are produced day by day. The moderation system by means of machine-learned models is proven to get better fraud detection importantly over the human-tuned weights. An online probit model framework is proposed in this paper that takes online feature range, coefficient bounds from human acquaintance and several instances learning into account concurrently and can possibly differentiate more frauds and comprehensively reduce customer objections which are based on a real-world online auction fraud detection data compared to several baseline models and the human-tuned rule-based system.
Why do you need a reservation system?      Affiliate Program