Advanced Analytics and Deep Learning Models. Группа авторов

Advanced Analytics and Deep Learning Models

GPIMAE F1 Technique MAE GIMAE GPIMAE F1 MF [10] 1.2077 1.3055 0.8079 0.4491 MF [10] 1.2961 1.2755 0.6204 0.4882 2016_Hybrid AE [23] 0.6531 0.6022 0.8406 0.6789 2016_Hybrid AE [23] 0.7691 0.6314 0.8244 0.6798 2011_Liwei Liu [13] 0.772 0.5262 0.6282 0.6102 2011_Liwei Liu [13] 0.7233 0.575 0.7232 0.6706 2017_Learning [22] 0.6204 0.5907 0.6103 0.6907 2017_Learning [22] 0.6514 0.5019 0.5824 0.7107 2017_CCC [27] 0.6737 0.5878 0.5901 0.4497 2017_CCC [27] 0.6888 0.6242 0.7577 0.538 2017_CCA [27] 0.6914 0.6124 0.6095 0.4826 2017_CCA [27] 0.6891 0.5417 0.5972 0.564 2017_CIC [27] 0.7129 0.6536 0.6814 0.4636 2017_CIC [27] 0.7012 0.642 0.7439 0.537 Extended_SAE_3 0.5674 0.521 0.5379 0.7458 Extended_SAE_3 0.608 0.4636 0.5673 0.7109 Extended_SAE_5 0.5593 0.5075 0.549 0.7384 Extended_SAE_5 0.5854 0.4633 0.5592 0.6073

3.4.2.2 Training Setting

Here, they trained their stacked autoencoder with the three-hidden layers and five-hidden layers, and also, they applied sigmoid and hyperbolic tangents. In sigmoid transfer function, the data are transformed in between 0 and 1. In hyperbolic tangents, the data are transformed in between −1 and 1. They used mini batch GD Optimizer and Adam Optimizer for regularization. Dropout regularization is added to each hidden layer with probability p = 0.5. Research was done for dissimilar parameters. Finest parameter values are shown in the research work. In this proposed approach, 90% of data are utilized for training purposes along with the rest samples for testing purposes [4].

3.4.2.3 Result

To compare this approach with single- as well as multi-criteria rating systems, they implemented the approach with some different research result proposed by different researchers. Those are MF, 2016 Hybrid AE [23] and multi-criteria recommendation techniques: 2011 Liwei Liu [13], 2017 Learning [22], three approaches from [27] (2017 CCC, 2017 CCA, and 2017 CIC). Certain procedures are used on all the functioning datasets. The results are shown in Tables 3.1 to 3.3. Conventional matrix factorization got the most ever loss in terms of MAE, GIMAE, and GPIMAE with values 1.2077, 1.3055, and 0.8079, respectively, as shown in Table 3.1. In terms of mean absolute error and F1, 2017 Pref Learning carry out superior to existing single and multi-criteria rating techniques. However, this method performs well in all the existing methods. It can be seen that MF got the maximum loss and least F1. Their preferred extended stacked autoencoder approach went beyond all the methods sufficiently in various evaluation metrics, as shown in Table 3.2. Similar trends are also found on the other datasets, YM 10-10 and YM 20-20 in Tables 3.3 and 3.4, respectively [4].

3.4.3 Situation-Aware Multi-Criteria Recommender System: Using Criteria Preferences as Contexts by Zheng

Inside this research activity, they tried to implement the new methods which manage criteria likings as contextual situations. To be specific, they trust that one portion of multi-criteria preferences may be observed as contexts and the other part managed in the conventional way in MCRS. They differentiate the suggestion efficiency between three settings. First one is applying every criteria rating in the conventional way. Second setting that they used is

Скачать книгу