Bayesian Regression Approach for Building and Stacking Predictive Models in Time Series Analytics

TL;DR

This paper introduces a Bayesian regression method for time series modeling and stacking multiple predictive models, enabling uncertainty estimation and risk assessment in forecasts, especially useful with limited historical data.

Contribution

The paper presents a hierarchical Bayesian regression approach for time series and a probabilistic stacking method that accounts for model uncertainty and domain knowledge.

Findings

Hierarchical Bayesian model effectively handles short data series.

Stacking models with Bayesian regression provide uncertainty estimates.

Risk assessment is integrated into the predictive modeling process.

Abstract

The paper describes the use of Bayesian regression for building time series models and stacking different predictive models for time series. Using Bayesian regression for time series modeling with nonlinear trend was analyzed. This approach makes it possible to estimate an uncertainty of time series prediction and calculate value at risk characteristics. A hierarchical model for time series using Bayesian regression has been considered. In this approach, one set of parameters is the same for all data samples, other parameters can be different for different groups of data samples. Such an approach allows using this model in the case of short historical data for specified time series, e.g. in the case of new stores or new products in the sales prediction problem. In the study of predictive models stacking, the models ARIMA, Neural Network, Random Forest, Extra Tree were used for the prediction on the first level of model ensemble. On the second level, time series predictions of these models on the validation set were used for stacking by Bayesian regression. This approach gives distributions for regression coefficients of these models. It makes it possible to estimate the uncertainty contributed by each model to stacking result. The information about these distributions allows us to select an optimal set of stacking models, taking into account the domain knowledge. The probabilistic approach for stacking predictive models allows us to make risk assessment for the predictions that are important in a decision-making process.