Since obtaining the k-neighbors for a user takes nearly the [51 J. Bobadilla, E. Serac Collaborative filtering whole time for finding the recommending items, the simplicity of the formula used for calculating the similarity function(used (61). Bobadilla, F. Serradilla, The incidence of sparsity on collaborative filtering for obtaining k-neighbors)is crucial so as to accelerate the process of finding recommendations. Since the formula used in the similar- [71J. Bobadilla, F. Serradilla. J. Bemal, A new collaborative filtering metric that ity function in our GA method(see Eq (1))is much simpler than the formulae involved in the classical metrics, our similarity [81J Bobadilla, F. Ortega, A Hernando, A collaborative filtering similarity measure functions based on the ga method let us make recommendations ased on singularities, Inf. Proc. Manage. (2011). faster than the one used for traditional metrics. 6. Conclusions In this paper we have presented a genetic algorithm method for [11]G M. Giaglis, Lekakos, Improving the prediction accuracy of recomm obtaining optimal similarity functions. The similarity functions ob- 410- 43 roches anchored on numan accors, Interac tained provide better quality and quicker results than the ones pro-(12 j.L Herlocker, J.A. Konstan, J.T. Riedl, L.G. Terveen, Evaluatin vided by the traditional metrics. Improvements can be seen in the ng recommender systems, ACM Trans. Inf. Syst. 22(1)( systems accuracy(MAE), in the coverage and in the precision [13 Y Ho, S Fong. Z Yan, A hybrid ga-based collaborative filtering model for online call recommendation quality measures. The proposed use of GAs applied to the rs is a novel approach ased on SoM cluster-indexing CBR, Exp. Syst. Appl. 25(2003)413-423. and has the main advantage that it can be used in all CF-based 5 systens, Int con service Syst. service Mange. (comms.d arce recommender be applied, as in many cases no reliable demographic information segmentation for personalized recommender systems, Artif Intell. Simulat. or content-based filtering information is available The GA-metric runs 42% as fast as the correlation, which is a on line shopping m arker. exepert s st with Ap reat advantage in RS, which are highly dependent on equipment [18]M Knights. Web 2.0. IET Comm Eng( 2007)30-35 overloads when many different recommendation requests are [191 J.A Konstan, B.N. Mille s: toward a personal recommende made simultaneously(user to user)or on costly off-line running (20)BKrul )(2004)437-476 processes (item to item). filing using large-scale demographic data. Artif Intell. Magaz. 18(2)(1997)3 aning to filter netnews, 12th Int. Conf Machine [22 P Li, S Yamada, A movie recommender system based on inductive learning. Our acknowledgement to the Movielens group and the FilmAf- [23] K]. Lin Building Web 2.0. Computer,(2007)101-102. finity. com and Netflix companies opulus, A N. Papadopoulus, P. Symeonidis, orative recommender systems: combining effectivenes Reference [25 M. Papagelis, D. Plexousakis, utsuras, Alleviating trust inference ger on of recommender 5)224-239 stems: a survey of the state-of-the-art and possible extensions, IEEE Trans. [26]C Porcel, E. Herrera-Viedma, Dealing with incomplete information in a fuzzy KnowL Data Eng17(6)(2005)734-749 Fuzzy-genetic approach to recommender 23(1)(2010)32-39 systems based on a novel hybrid user model, Exp. Syst. AppL.(2008)1386- [271 C. Porcel, J.M. Moreno, E. Herrera-Viedma, A multi-disciplinar recommender ources in university digital libraries, Exp. Syst. [3I J.T. Alander, On optimal population size of genetic algorithms, Comput. Syst ppL.36(2009)12520-12528 [28 F. Zhang, H.Y. Chang. A collaborative filtering algorithm enetic 4] N. Antonopoulus, J. Salter, Cinema screen recommender agent: combining ering to ameliorate the scalability issue, IEEE Int. Con Eng collaborative and content-based filtering. IEEE Intell. Syst. (2006)35-41 (2006)331-338Since obtaining the k-neighbors for a user takes nearly the whole time for finding the recommending items, the simplicity of the formula used for calculating the similarity function (used for obtaining k-neighbors) is crucial so as to accelerate the process of finding recommendations. Since the formula used in the similar￾ity function in our GA method (see Eq. (1)) is much simpler than the formulae involved in the classical metrics, our similarity functions based on the GA method let us make recommendations faster than the one used for traditional metrics. 6. Conclusions In this paper we have presented a genetic algorithm method for obtaining optimal similarity functions. The similarity functions ob￾tained provide better quality and quicker results than the ones pro￾vided by the traditional metrics. Improvements can be seen in the system’s accuracy (MAE), in the coverage and in the precision & re￾call recommendation quality measures. The proposed use of GAs applied to the RS is a novel approach and has the main advantage that it can be used in all CF-based RS, without the need to use hybrid models which often cannot be applied, as in many cases no reliable demographic information or content-based filtering information is available. The GA-metric runs 42% as fast as the correlation, which is a great advantage in RS, which are highly dependent on equipment overloads when many different recommendation requests are made simultaneously (user to user) or on costly off-line running processes (item to item). Acknowledgements Our acknowledgement to the MovieLens Group and the FilmAf- finity.com and Netflix companies. References [1] G. Adomavicius, A. Tuzhilin, Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions, IEEE Trans. Knowl. Data Eng. 17 (6) (2005) 734–749. [2] M.Y. Al-Shamri, K.K. Bharadwaj, Fuzzy-genetic approach to recommender systems based on a novel hybrid user model, Exp. Syst. Appl. (2008) 1386– 1399. [3] J.T. Alander, On optimal population size of genetic algorithms, Comput. Syst. SoftwareEng. (1992) 65–70. [4] N. Antonopoulus, J. Salter, Cinema screen recommender agent: combining collaborative and content-based filtering, IEEE Intell. Syst. (2006) 35–41. [5] J. Bobadilla, F. Serradilla, A. Hernando, Collaborative filtering adapted to recommender systems of e-learning, Knowl. Based Syst. 22 (2009) 261–265. [6] J. Bobadilla, F. Serradilla, The incidence of sparsity on collaborative filtering metrics, Australian Database Conf. ADC 92 (2009) 9–18. [7] J. Bobadilla, F. Serradilla, J. Bernal, A new collaborative filtering metric that improves the behavior of recommender systems, Knowl. Based Syst. 23 (6) (2010) 520–528. [8] J. Bobadilla, F. Ortega, A. Hernando, A collaborative filtering similarity measure based on singularities, Inf. Proc. Manage. (2011), doi:10.1016/ j.ipm.2011.03.007. [9] H. Denis. Managing collaborative learning processes, e-learning applications. 29th Int. Conf. Inf. Tech. Interfaces, (2007) 345–350. [10] L.Q. Gao, C. Li, Hybrid personalizad recommended model based on genetic algorithm, Int. Conf. Wireless Comm. Netw. Mobile Comput. (2008) 9215– 9218. [11] G.M. Giaglis, Lekakos, Improving the prediction accuracy of recommendation algorithms: approaches anchored on human factors, Interact. Comp. 18 (3) (2006) 410–431. [12] J.L. Herlocker, J.A. Konstan, J.T. Riedl, L.G. Terveen, Evaluating collaborative filtering recommender systems, ACM Trans. Inf. Syst. 22 (1) (2004) 5–53. [13] Y. Ho, S. Fong, Z. Yan, A hybrid ga-based collaborative filtering model for online recommenders, Int. Conf. e-Business (2007) 200–203. [14] H. Ingoo, J.O. Kyong, H.R. Tae, The collaborative filtering recommendation based on SOM cluster-indexing CBR, Exp. Syst. Appl. 25 (2003) 413–423. [15] H. Jinghua, W. Kangning, F. Shaohong, A survey of e-commerce recommender systems, Int. Conf. Service Syst. Service Manage. (2007) 1–5. [16] K. Kim, H. Ahn, Using a clustering genetic algorithm to support customer segmentation for personalizad recommender systems, Artif. Intell. Simulat. 3397 (2004) 409–415. [17] K. Kim, H. Ahn, A recommender system using GA K-means clustering in an online Shopping market, Expert Syst. with Appl. 34 (2) (2008) 1200–1209. [18] M. Knights. Web 2.0. IET Comm. Eng. (2007) 30–35. [19] J.A. Konstan, B.N. Miller, J. Riedl, PocketLens: toward a personal recommender system, ACM Trans. Inf. Syst. 22 (3) (2004) 437–476. [20] B. Krulwich, Lifestyle finder: intelligent user profiling using large-scale demographic data, Artif. Intell. Magaz. 18 (2) (1997) 37–45. [21] K. Lang. NewsWeeder: Learning to filter netnews, 12th Int. Conf. Machine Learning, (1995) 331–339. [22] P. Li, S. Yamada, A movie recommender system based on inductive learning, IEEE Conf. Cyber. Intell. Syst. 1 (2004) 318–323. [23] K.J. Lin. Building Web 2.0. Computer, (2007) 101–102. [24] Y. Manolopoulus, A. Nanopoulus, A.N. Papadopoulus, P. Symeonidis, Collaborative recommender systems: combining effectiveness and efficiency, Exp. Syst. Appl. 34 (4) (2008) 2995–3013. [25] M. Papagelis, D. Plexousakis, T. Kutsuras, Alleviating the sparsity problem of collaborative filtering using trust inferences, LNCS 3477 (2005) 224–239. [26] C. Porcel, E. Herrera-Viedma, Dealing with incomplete information in a fuzzy linguistic recommender system to diseminate information in university digital libraries, Knowl. Based Syst. 23 (1) (2010) 32–39. [27] C. Porcel, J.M. Moreno, E. Herrera-Viedma, A multi-disciplinar recommender system to advice research resources in university digital libraries, Exp. Syst. Appl. 36 (2009) 12520–12528. [28] F. Zhang, H.Y. Chang, A collaborative filtering algorithm employing genetic clustering to ameliorate the scalability issue, IEEE Int. Conf. e-Business Eng. (2006) 331–338. 1316 J. Bobadilla et al. / Knowledge-Based Systems 24 (2011) 1310–1316