Keywords: Genomic selection GBLUP Item Based Collaborative Filtering Comparison Prediction accuracy
Montesinos-Lopez, O. A., Franco-Perez, E., Luna-Vázquez, F. J., Salinas-Ruiz, J., Sandoval Carrillo, S., Valenzo-Jiménez, M. A., Cuervas, J. & Santana-Mancilla, P. C. (2020). Benchmarking between item based collaborative filtering algorithm and genomic best linear unbiased prediction (GBLUP) model in terms of prediction accuracy for wheat and maize. Biotecnia, 22(2). https://doi.org/10.18633/biotecnia.v22i2.1255.
2020 Biotecnia
URL: https://doi.org/10.18633/biotecnia.v22i2.1255
Aim/background: in view of the growing demand for food, new methodologies are needed to improve the genomic selection (GS) methodology to obtain more productive plant varieties and there is empirical evidence that GS it is revolutionizing plant breeding for food production around the world. Methods: since the prediction models play a key role in GS, for this reason Montesinos-López et al. (2018) proposed the item based collaborative filtering (IBCF) algorithm for Genomic prediction. For this reason, in this paper we compare the IBCF algorithm with the most popular genomic prediction model called the Genomic Best Linear Unbiased Prediction (GBLUP). Results: We found that the GBLUP is superior than the IBCF model, but the IBCF is competitive to the GBLUP model since produced very similar predictions, but with the large advantage that it is extremely efficient in terms of time for implementation. Conclusions: we found that the GBLUP is better than the IBCF algorithm but the IBCF is more than 400 times more efficient than the GBLUP model in terms of time for implementation. Limitations: The main limitation of the study is that it was performed in univariate terms and it is possible that the IBCF will perform better with multivariate data.