Prediction of rare events in the operation of household equipment using co-evolving time series

In this study, we propose a probabilistic approach to predict rare events by exploiting coevolving time series. The probability of a failure is calculated based on the weighted autologistic regression of these time series, accounting for specific characteristics of failures such as data imbalance. We estimate the model parameters using the maximum likelihood of the Bernoulli process. By incorporating the temporal behaviors of the various phenomena underlying the occurrence of failures and the nature of the data, we improve the prediction of rare events. Evaluations on both synthetic and real datasets demonstrate that our approach outperforms existing methods in predicting home equipment failures.