Online PSO for Web Marketing Optimization

International Journal of Science and Research (IJSR), ISSN (Online): 2319-7064, 2014

In the age of digital and network, every high efficiency and high profit activity has to harmonize with internet. The business behaviors and activities always are the precursor for getting high efficiency and high profit. Consequently, each business behavior and activities have to adjust for integrating with internet. Underlay on the internet, business extension and promotion behaviors and activities general are called the Electronic Commerce (E-commerce). The quality of web-based customer service is the capability of a firm's website to provide individual heed and attention. Today scenario personalization has become a vital business problem in various e-commerce applications, ranging from various dynamic web content presentations. In our paper Iterative technique partitions the customer in terms of frankly combining transactional data of various consumers that forms dissimilar customer behavior for each group, and best customers are acquired, by applying approach such as, IE (Iterative Evolution), ID (Iterative Diminution) and II (Iterative Intermingle) algorithm. The excellence of clustering is improved via Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO). In this paper these two algorithms are compared and it is found that Iterative technique chorus Particle Swarm Optimization (PSO) is better than the other Ant Colony Optimization (ACO) algorithms. Additionally the results show that the Particle Swarm Optimization (PSO) algorithm outperforms other Ant Colony Optimization (ACO) algorithms methods. Finally quality is superior along with this response time higher and cost wise performance is increased and both accuracy and efficiency.

Proceedings of the 2003 IEEE Swarm …, 2003

IJRET, 2013

The rapid growth of web pages available on the Internet recently, searching relevant and up-to-date information has become a crucial issue. Information retrieval is one of the most crucial components in search engines and their optimization would have a great effect on improving the searching efficiency due to dynamic nature of web it becomes harder to find relevant and recent information. That’s why more and more people begin to use focused crawler to get information in their special fields today. Conventional search engines use heuristics to determine which web pages are the best match for a given keyword. Earlier results are obtained from a database that is located at their local server to provide fast searching. However, to search for the relevant and related information needed is still difficult and tedious. This paper presents a model of hybrid Genetic Algorithm -Particle Swarm Optimization (HGAPSO) for Web Information Retrieval. Here HGAPSO expands the keywords to produce the new keywords that are related to the user search

International Journal of Computer Applications, 2014

There is a tremendous proliferation in the amount of information available on the largest shared information source, the World Wide Web. Due to its wide distribution, openness and highly dynamic data, the resources on the web are greatly scattered and they have no unified management and structure. Near about 90 % web data is unstructured and needed to be structure as it greatly reduces the efficiency in using web information. Web text feature extraction and clustering are the main challenging tasks in web data mining, which requires an efficient clustering technique. Data mining tasks require fast and accurate partitioning of huge unstructured data which may come with a variety of dimensions and attribute. In our paper we are focusing on the different clustering techniques, helpful for web data clustering. For such novel approach we perform a literature survey and depicted an evolutionary bio-inspired Swarm Intelligence algorithm called Particle Swarm Optimization (PSO) for optimized clustering result. In order to preprocess input data for improving the accuracy and optimize keyword searching, stop word removal and stemming methods are used. PSO algorithm will greatly improve the efficiency of web texts processing, and such evolutionary clustering techniques are used for web text data clustering.

European Journal of Operational Research, 2007

In today's competitive electronic marketplace, companies try to create long-lasting relations with their online customers. Log files and registration forms generate millions of online transactions. Companies use new techniques to ''mine'' these data and establish optimal online storefronts to maximize their web presence. Several criteria, such as minimization of download time, maximization of web-site visualization and product association level, can be used for the optimization of virtual storefronts. This paper introduces a genetic algorithm, to be used in a model-driven decision-support system for web-site optimizations. The algorithm ensures multiple criteria web-site optimizations, and the genetic search provides dynamic and timely solutions independent of the number of objects to be arranged.

2008

Particle Swarm Optimisation (PSO) is an optimisation technique based on the principle of social influence. It has been applied successfully on a wide range of optimisation problems. This paper considers the possibility of a dynamic hierarchical extension to the particle swarm technique, allowing the swarm to consider several related datasets. This provides the advantage of being able to consider several data scans and aggregate the results into a master swarm model.

Industrial Engineering and Management, 2015

Here, a collection of base functions and sub-functions configure the nodes of a web-based (digital)network representing functionalities. Each arc in the network is to be assigned as the link between two nodes. The aim is to find an optimal tree of functionalities in the network adding value to the product in the web environment. First, a purification process is performed in the product network to assign the links among bases and sub-functions. Then, numerical values as benefits and costs are determined for arcs and nodes, respectively. To handle the bi-objective Steiner tree, a particle swarm optimization algorithm is adapted to find the optimal tree determining the value adding sub-functions to bases in a convergent product. An example is worked out to illustrate the applicability of the proposed approach.

International Journal of Computational Intelligence Systems

Successful blogs receive high ratings and generate marketing value. What factors contribute to the success of a blog and how to predict its success level are questions worth discussing. A hybrid swam intelligence approach is proposed in this study to predict blog success level. First, this study develops a research model of blog success with six factors from content, technology, and social views of point, which include currentness, design, reliability, security, interaction, and connectivity. A questionnaire is designed based on the blog success model. Two hundred ten valid samples are collected from Internet users with experience in using or creating blogs. A hybrid approach combining particle swarm optimization (PSO) and self-organizing map (SOM) is proposed to predict blog success level. The results of 10-fold validation are examined to compare the hybrid PSO-SOM approach with the results from three classifiers: C5.0, classification and regression trees (CARTs), and support vector machine (SVM). For blog success prediction, the results indicate the PSO-SOM approach demonstrates higher accuracy among these methods.

Content marketing is today's one of the trendiest marketing approaches employed by companies. Because of its connections with especially social media, it is always important to obtain effective content marketing processes in the context of a dynamic, flexible communication environment. So, there is a remarkable research interest in making everything better for content marketing. In this paper, it is aimed to develop a software system, which is able to use artificial intelligence for optimizing parameters of a content that may be provided over popular social media environments for marketing purposes. By optimizing the content according to feedbacks from users, it is thought that next presentation of the content may result to improved interest by objective users. Here, it has been tried to be done thanks to a software system.

International Journal of Knowledge Discovery in Bioinformatics, 2016

Due to rapid digital explosion user shows interest towards finding suggestions regarding a particular topic before taking any decision. Nowadays, a movie recommendation system is an upcoming area which suggests movies based on user profile. Many researchers working on supervised or semi-supervised ensemble based machine learning approach for matching more appropriate profiles and suggest related movies. In this paper a hybrid recommendation system is proposed which includes both collaborative and content based filtering to design a profile matching algorithm. A nature inspired Particle Swam Optimization technique is applied to fine tune the profile matching algorithm by assigning to multiple agents or particle with some initial random guess. The accuracy of the model will be judged comparing with Genetic algorithm.