Papers by S. Alireza Hashemi Golpayegani
Anomaly Detection in Q & A Based Social Networks
Proceedings of the Future Technologies Conference (FTC) 2018, 2018
Detection of anomalies in question/answer based social networks is important in terms of finding ... more Detection of anomalies in question/answer based social networks is important in terms of finding the best answers and removing unrelated posts. These networks are usually based on users’ posts and comments, and the best answer is selected based on the ratings by the users. The problem with the scoring systems is that users might collude in rating unrelated posts or boost their reputation. Also, some malicious users might spam the discussion. In this paper, we propose a network analysis method based on network structure and node property for exploring and detecting these anomalies.
In many cases, financial indicators are used for market analysis and to forecast the future of st... more In many cases, financial indicators are used for market analysis and to forecast the future of stock prices. Due to the high complexity of the stock market, determining which indicators should be used and the reliability of their outcomes have always been a challenge. In this article, a hybrid approach in the form of a decision support system is being introduced that offers the best suggestions in buying and selling stocks. This system will help an investor to identify the best portfolio of stocks using a series of financial indicators. These indices act as a model that forecast the future price of a stock by examining its activities and status in the past. Therefore, using a combination of the indices enables us to make decisions with more certainty. Proficiency of this system has been evaluated through the collection of data from the stock market in Iran from 2001 through 2011. The results show that the use of indices and their combination have led to the decision support system t...
QoS-CBMG: A Model for e-Commerce Customer Behavior
World Academy of Science, Engineering and Technology, International Journal of Computer and Information Engineering, 2016
An effective recommender system based on personality traits, demographics and behavior of customers in time context
Data Technologies and Applications, 2020
PurposeImproving the performance of recommender systems (RSs) has always been a major challenge i... more PurposeImproving the performance of recommender systems (RSs) has always been a major challenge in the area of e-commerce because the systems face issues such as cold start, sparsity, scalability and interest drift that affect their performance. Despite the efforts made to solve these problems, there is still no RS that can solve or reduce all the problems simultaneously. Therefore, the purpose of this study is to provide an effective and comprehensive RS to solve or reduce all of the above issues, which uses a combination of basic customer information as well as big data techniques.Design/methodology/approachThe most important steps in the proposed RS are: (1) collecting demographic and behavioral data of customers from an e-clothing store; (2) assessing customer personality traits; (3) creating a new user-item matrix based on customer/user interest; (4) calculating the similarity between customers with efficient k-nearest neighbor (EKNN) algorithm based on locality-sensitive hashi...
Website user content navigation behavior modeling using time series neural networks
Web Intelligence, 2019
A QoS sensitive model for e-commerce customer behavior
Journal of Research in Interactive Marketing, 2017
Purpose In this paper, a Quality of Service-sensitive customer behavior model graph (QoS-CBMG) is... more Purpose In this paper, a Quality of Service-sensitive customer behavior model graph (QoS-CBMG) is proposed for use in service quality adaptation in e-commerce systems. Success in achieving customer satisfaction and maximizing profit in e-commerce is highly dependent on the QoS provided. However, providing high-level QoS for all customers in all Web sessions is often deemed costly and inefficient. Therefore, a QoS-sensitive model for formulating QoS-aware offers to customers is required. The paper aims to respond to this necessity. Design/methodology/approach Process mining is adopted as the knowledge extraction technique for developing a QoS-CBMG. If it is assumed that user navigation on a website is a process, then clickstreams during one user’s navigations can be considered process steps. Findings The application of both QoS-CBMG (the new model) and CBMG (the classic version) to the same real data set demonstrated that the proposed method outperforms CBMG due to its reduction of a...
Personalized recommender system based on social relations
2016 24th Iranian Conference on Electrical Engineering (ICEE), 2016
Advent of the Social Web and the ever increasing popularity of Web 2.0 applications, has led to a... more Advent of the Social Web and the ever increasing popularity of Web 2.0 applications, has led to a massive amount of information. Therefore, users have difficulties in finding their desired information according to their interests and preferences. To address this issue, recommender systems have been emerged. These systems try to provide users with the most relevant and suitable information they need by investigating their preferences as well as their demographic information. With the growing development of social networks and the number of users in them, the value of information in these systems has also increased. This information in social networks can be used to improve the precision of recommender systems. In this paper we present a novel recommender system that makes use of user's social relationships in two levels: computing the similarity between them and identifying user's neighbors set. Our experimental results show that the proposed model outperforms Collaborative Filtering (CF) based recommender system in terms of recommendation accuracy.
Social network analysis emerged as an important research topic in sociology decades ago, and it h... more Social network analysis emerged as an important research topic in sociology decades ago, and it has also attracted scientists from various fields of study like psychology, anthropology, geography and economics. In recent years, a significant number of researches has been conducted on using social network analysis to design e-commerce recommender systems. Most of the current recommender systems are designed for B2C e-commerce websites. This paper focuses on building a recommendation algorithm for C2C e-commerce business model by considering special features of C2C e-commerce websites. In this paper, we consider users and their transactions as a network; by this mapping, link prediction technique which is an important task in social network analysis could be used to build the recommender system. The proposed tow-level recommendation algorithm, rather than topology of the network, uses nodes' features like: category of items, ratings of users, and reputation of sellers. The results show that the proposed model can be used to predict a portion of future trades between users in a C2C commercial network.
2015 7th Conference on Information and Knowledge Technology (IKT), 2015
Nowadays, with the great development of electronic commerce, there exist lots of online marketpla... more Nowadays, with the great development of electronic commerce, there exist lots of online marketplaces, each of which presents a different payment method to their customers. However, the remarkable point is that although there are few websites which offer their customers after-delivery payment methods, there does not exist a website which presents dynamic payment methods to their customers according to their trust level. Therefore, a piece of research needs to be done on different payment methods and their relation with the trust level of the buyer and the seller. In this paper, not only is this relation covered, but also a computational model is examined that can calculate the trust level between the buyer and the seller by means of seller, buyer, and transaction parameters. Moreover, the model offers the best payment parameters that maximizes the trust level of the buyer and the seller. This way, the transaction becomes more probable to happen.
Proceedings of the 13th International Conference on Electronic Commerce - ICEC '11, 2012
Collaborative filtering (CF) is a popular method for personalizing product recommendations for e-... more Collaborative filtering (CF) is a popular method for personalizing product recommendations for e-commerce applications. In order to recommend a product to a user and predict her preference, CF utilizes product evaluation ratings of the like-minded users. This process of finding the like-minded users causes a social network to be formed among all users. In this social network, each link between a couple of users presents an implicit connection between them. Here, there are some users who have more connections with others and are called the most influential users. This paper attempts to model and analyze the behavior of these users by employing data mining techniques. First, the most important features which present a user's influence were selected with a linear regression method, and then, the modeling was performed by a decision tree. Based on our results, the most influential users are users who show more interest to rate more than average number of items with low frequency. Moreover, other most influentials are users who rate in moderation items which have been seen in moderation. In addition, these items are rated with good degree of agreement with other users' rates on the items. We achieved a high accuracy with this model.
Optimizing information systems by realizing the autonomy around business
2009 14th International CSI Computer Conference, 2009
With ever increasing complexity of software systems, it is now more evident than ever that a fund... more With ever increasing complexity of software systems, it is now more evident than ever that a fundamental change in software engineering practices is required. In this paper we discuss the nature of change and its implications. The notion of passive autonomy is introduced as a reference to the relative autonomy of business entities, and we claim that realizing the passive
The logical precedence network planning of projects, considering the finish-to-start (FS) relations, using neural networks
The International Journal of Advanced Manufacturing Technology, 2011
One of the important steps in the process of project planning is the designing of logical precede... more One of the important steps in the process of project planning is the designing of logical precedence network. As the procedure of the logical precedence network planning is case dependent and varies in different projects, it could be considered as an unstructured and complex problem which should be solved by implementing the implicit domain knowledge of the planner. In this
International Journal of Computer and Communication Technology, 2010
The internet conceptualized new ways of social interaction, activities globally. Internet serves ... more The internet conceptualized new ways of social interaction, activities globally. Internet serves billions of users worldwide. By the end of 2011it is expected that 22% of the world’s population will regularly surf internet. Beside this, internet incorporated high risks for e-users by enabling intruders to gain access via security holes. Network security is a course of action for assuring data from illicit accessing, exploitation, exposure, damage, alteration, or disorders related to the impulsive growth of popularity of e-users. Cellular Automata (CA) has been recommended in favor of the potential usage of data security. Single Electron devices (SED) have unanimously contributed in significant reduction of size of electronic devices and are now weighed up as the best substitute of future device family. Here we address a novel adaptive method to assimilate CA using SED in data security.
Designing work breakdown structures using modular neural networks
Decision Support Systems, 2007
IJBISS, 2012
In many cases, financial indicators are used for market analysis and to forecast the future of st... more In many cases, financial indicators are used for market analysis and to forecast the future of stock prices. Due to the high complexity of the stock market, determining which indicators should be used and the reliability of their outcomes have always been a challenge. In this article, a hybrid approach in the form of a decision support system is being introduced that offers the best suggestions in buying and selling stocks. This system will help an investor to identify the best portfolio of stocks using a series of financial indicators. These indices act as a model that forecast the future price of a stock by examining its activities and status in the past. Therefore, using a combination of the indices enables us to make decisions with more certainty. Proficiency of this system has been evaluated through the collection of data from the stock market in Iran from 2001 through 2011. The results show that the use of indices and their combination have led to the decision support system to produce suggestions with very high precisions.
The logical precedence network planning of projects, considering the finish-to-start (FS) relations, using neural networks
Abstract One of the important steps in the process of
project planning is the designing of logica... more Abstract One of the important steps in the process of
project planning is the designing of logical precedence
network. As the procedure of the logical precedence
network planning is case dependent and varies in different
projects, it could be considered as an unstructured and
complex problem which should be solved by implementing
the implicit domain knowledge of the planner. In this paper,
we have shown how the artificial neural networks could be
implemented to plan the finish-to-start logical precedence
network of projects. The implementation results depict that
the proposed methodology could result reasonable, accu-
rate, and reliable outcomes, which could be used as a
primary solution, which can enrich the acquired knowledge,
after the accomplishment of the project and its practical
corrections.
Designing work breakdown structures using modular neural networks
In this paper, a framework which employs neural networks to plan the work breakdown structure of ... more In this paper, a framework which employs neural networks to plan the work breakdown structure of projects has been
introduced. Using the proposed framework, a modular neural network has been developed to plan the structures of a limited project
domain. The main concepts of the Andishevaran Methodology of Project Management (AMPM), including project control work
breakdown structure (PCWBS), functional work breakdown structure (FWBS) and relational work breakdown structure (RWBS),
have used to form the outputs of the model and its modules. The nature of projects, which have been represented by a limited set of
attributes, are considered as the main inputs of the model. The independency from project domains is the main advantage of the
proposed framework. The framework has been tested on a sample domain, and results showed that the planned work breakdown
structures and activities have satisfied the expectations with different levels of validity. Therefore the model outputs could be
considered as the primary plan of project structures which could be improved by some modifications.
© 2007 Elsevier B.V. All rights reserved.
Optimizing Information Systems By Realizing the Autonomy around Business
With ever increasing complexity of software systems, it
is now more evident than ever that a fund... more With ever increasing complexity of software systems, it
is now more evident than ever that a fundamental
change in software engineering practices is required.
In this paper we discuss the nature of change and its
implications. The notion of passive autonomy is
introduced as a reference to the relative autonomy of
business entities, and we claim that realizing the
passive autonomy in information systems would results
in systems far more adaptable and aligned with
business’ needs. In order to realize this autonomy,
theuse of autonomous agents as representing real
world autonomous entities is suggested. After pointing
out the shortcomings of current agent based
architectures, a new architecture is proposed, based on
indirect, multilateral negotiation. The suitability of this
architecture is demonstrated in a simple case of beer
game and it is shown that the bullwhip effect is
remedied to some extent using this new architectural
approach.
Uploads
Papers by S. Alireza Hashemi Golpayegani
project planning is the designing of logical precedence
network. As the procedure of the logical precedence
network planning is case dependent and varies in different
projects, it could be considered as an unstructured and
complex problem which should be solved by implementing
the implicit domain knowledge of the planner. In this paper,
we have shown how the artificial neural networks could be
implemented to plan the finish-to-start logical precedence
network of projects. The implementation results depict that
the proposed methodology could result reasonable, accu-
rate, and reliable outcomes, which could be used as a
primary solution, which can enrich the acquired knowledge,
after the accomplishment of the project and its practical
corrections.
introduced. Using the proposed framework, a modular neural network has been developed to plan the structures of a limited project
domain. The main concepts of the Andishevaran Methodology of Project Management (AMPM), including project control work
breakdown structure (PCWBS), functional work breakdown structure (FWBS) and relational work breakdown structure (RWBS),
have used to form the outputs of the model and its modules. The nature of projects, which have been represented by a limited set of
attributes, are considered as the main inputs of the model. The independency from project domains is the main advantage of the
proposed framework. The framework has been tested on a sample domain, and results showed that the planned work breakdown
structures and activities have satisfied the expectations with different levels of validity. Therefore the model outputs could be
considered as the primary plan of project structures which could be improved by some modifications.
© 2007 Elsevier B.V. All rights reserved.
is now more evident than ever that a fundamental
change in software engineering practices is required.
In this paper we discuss the nature of change and its
implications. The notion of passive autonomy is
introduced as a reference to the relative autonomy of
business entities, and we claim that realizing the
passive autonomy in information systems would results
in systems far more adaptable and aligned with
business’ needs. In order to realize this autonomy,
theuse of autonomous agents as representing real
world autonomous entities is suggested. After pointing
out the shortcomings of current agent based
architectures, a new architecture is proposed, based on
indirect, multilateral negotiation. The suitability of this
architecture is demonstrated in a simple case of beer
game and it is shown that the bullwhip effect is
remedied to some extent using this new architectural
approach.