Abstract: The users of social network sites are always constructing a large network, recommending friends to registered users is a crucial task for these sites. Traditional content- based or collaborative filtering recommend technologies are limited for the task, because the users and items are the same dataset, which have rich attributes and complex social graph. In the paper, we proposed a local random walk and random forests combined method to do friends recommendation for large social networks. The experimental results show that the method has high precision and high recall at the same time.

• Publication Date: 17-Nov-2014
• DOI: 10.15224/978-1-63248-051-4-91
• Views: 0
• Downloads: 0

Abstract: First-come-first-serve (FCFS) scheme is used for selling the goods in market that is a multi-million dollar industry for any popular event. But in a competitive environment is this FCFS efficient? In earlier literature it has been shown that the auction based alternative solutions using the framework of mechanism design, a sub field of game theory [18] can provide better results against FCFS in terms of profit making and efficiency in allocation. However the solution proposed in the earlier literature can address the selling environment where an agent can give demand for a single good that is they have single/Multi unit demand. However there might be a situation where a seller wishes to sell in the combination of goods and buyer wishes to buy in some combinations. It is highly difficult to solve a combinatorial double auction where sellers and buyers bids simultaneously. In this paper we proposed two algorithms of which one is truthful produces a solution which is very near to optimal

• Publication Date: 17-Nov-2014
• DOI: 10.15224/978-1-63248-051-4-92
• Views: 0
• Downloads: 0