Identifying "Promising" Internet Business Applications Using Artificial Neural Networks

Now a day's almost all companies, no matter big or small, have their website. This website may either be only for promotional purposes i.e. "passive" or it might also incorporate certain online features which tend to make it "active". Presently the number and the diversity of internet applications are huge and still growing very fast. Any business website ensuring issues of "security" and "user interaction" will surely be successful in achieving its goal - increased online business. This would in turn make this particular site "Promising" for both the end users and the firm to which it belongs. In this paper, we present an approach wherein we are creating a web portal, which is in process of being filled with "Promising" internet business applications. The purpose of this Internet Business Portal (IBP) is to document the state-of-the-art of business web use, with a focus on business-to-business and business-to-consumer applications. Neural networks are attractive for classification problems because they are capable to learn from noisy data and to generalize. In this paper the multi-layer perceptron, modular neural networks are being considered. An accuracy of 84 % was obtained.