A recommender system based on invasive weed optimization algorithm

被引：74

作者：

Rad, Hoda Sepehri ^{[1
]}

Lucas, Caro ^{[2
]}

机构：

[1] Univ Tehran, Robot & Machine Intelligence Grp, Sch Elect & Comp Engn, Coll Engn, POB 11365-4563, Tehran, Iran

[2] Univ Tehran, Control & Intelligent Proc Ctr Excellence, Sch Elect & Comp Engn, Coll Engn, Tehran, Iran

来源：

2007 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-10, PROCEEDINGS | 2007年

关键词：

D O I：

10.1109/CEC.2007.4425032

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recommender systems intend to help users find their interested items from among a large number of items. We continue our previous work that emphasizes on "prioritized user-profile" approach as an effective approach to increase the quality of the recommendations. Prioritized user-profile is an approach that tries to implement more personalized recommendation by assigning different priority importance to each of the features of the user-profile for different users. In order to find the optimal priorities for each user an optimization algorithm is needed. In this paper, we employ a new optimization algorithm namely Invasive Weed Optimization (IWO) for this purpose. IWO is a relatively new and simple algorithm inspired from the invasive habits of growth of weeds in nature. Experimental results showed that IWO achieved the best accuracy in predicting users' interests compared to two other prioritized approaches which were based on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) and to standard user-based Pearson algorithm on a movie dataset.

引用

页码：4297 / +

页数：2

共 10 条

[1]

BREESE H, 1998, EMPIRICAL ANAL PREDI

[2]

Eberhart RC, 2001, IEEE C EVOL COMPUTAT, P81, DOI 10.1109/CEC.2001.934374

[3]

HERLOCKER J, 1999, P ACM SIGIR

[4] Evaluating collaborative filtering recommender systems [J].