Selecting Data Adaptive Learner from Multiple Deep Learners using Bayesian Networks
This is an incremental improvement for financial forecasting, potentially enhancing prediction robustness in that domain.
The authors tackled the problem of predicting financial time-series by proposing a method that selects among multiple deep learners using a Bayesian network, achieving robust predictions as demonstrated on the Nikkei 225 index.
A method to predict time-series using multiple deep learners and a Bayesian network is proposed. In this study, the input explanatory variables are Bayesian network nodes that are associated with learners. Training data are divided using K-means clustering, and multiple deep learners are trained depending on the cluster. A Bayesian network is used to determine which deep learner is in charge of predicting a time-series. We determine a threshold value and select learners with a posterior probability equal to or greater than the threshold value, which could facilitate more robust prediction. The proposed method is applied to financial time-series data, and the predicted results for the Nikkei 225 index are demonstrated.