The impact of data set similarity and diversity on transfer learning success in time series forecasting

Models, pre-trained on a similar or diverse source data set, have become pivotal in enhancing the efficiency and accuracy of time series forecasting on target data sets by leveraging transfer learning. While benchmarks validate the performance of model generalization on various target data sets, there is no structured research providing similarity and diversity measures explaining which characteristics of source and target data lead to transfer learning success. Our study pioneers in systematically evaluating the impact of source-target similarity and source diversity on zero-shot and fine-tuned forecasting outcomes in terms of accuracy, bias, and uncertainty estimation. We investigate these dynamics using pre-trained neural networks across five public source datasets, applied in forecasting five target data sets, including real-world wholesales data. We identify two feature-based similarity and diversity measures showing: Source-target similarity enhances forecasting accuracy and reduces bias, while source diversity enhances forecasting accuracy and uncertainty estimation and increases the bias.

Hierarchical Neural Additive Models for Interpretable Demand Forecasts

Demand forecasts are the crucial basis for numerous business decisions, ranging from inventory management to strategic facility planning. While machine learning (ML) approaches offer accuracy gains, their interpretability and acceptance are notoriously lacking. Addressing this dilemma, we introduce Hierarchical Neural Additive Models for time series (HNAM). HNAM expands upon Neural Additive Models (NAM) by introducing a time-series specific additive model with a level and interacting covariate components. Covariate interactions are only allowed according to a user-specified interaction hierarchy. For example, weekday effects may be estimated independently of other covariates, whereas a holiday effect may depend on the weekday and an additional promotion may depend on both former covariates that are lower in the interaction hierarchy. Thereby, HNAM yields an intuitive forecasting interface in which analysts can observe the contribution for each known covariate. We evaluate the proposed approach and benchmark its performance against other state-of-the-art machine learning and statistical models extensively on real-world retail data. The results reveal that HNAM offers competitive prediction performance whilst providing plausible explanations.