Consensus or ensemble models

Numerous QSAR tools have been developed [152, 154] and used in modeling physicochemical data. These vary from simple linear to more complex nonlinear models, as well as classification models. A popular approach more recently became the construction of consensus or ensemble models ( combinatorial QSAR ) combining the predictions of several individual approaches [155]. Or, alternatively, models can be built by rurming the same approach, such as a neural network of a decision tree, many times and combining the output into a single prediction. 

These techniques span the entire field from multiple linear regression (MLR)-type methods and various forms of neural network architectures to rule-based techniques of different kinds. These approaches also span from single models to multiple models, that is, consensus or ensemble modeling. Terms like machine learning and data or information fusion are also frequently encountered in this area of research, as well as the concepts of applicability domain and validation. 

Since the nature of the data set is not always clear, a good approach in prediction is to build a consensus model using a combination of several methods. There are different ways of achieving this. One is to run the same approach, for example, a neural network, many times and build an ensemble or committee model. The other is to use several approaches, for example, PLS, RE, NN, and calculate the weighted or unweighted average in a consensus model. The advantage is that you cover various aspects of the nature of the data and each individual model uses a potentially different descriptor subset. 

---