REVIEW 3 cited by
MQRetNN: Multi-Horizon Time Series Forecasting with Retrieval Augmentation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Multi-horizon probabilistic time series forecasting has wide applicability to real-world tasks such as demand forecasting. Recent work in neural time-series forecasting mainly focus on the use of Seq2Seq architectures. For example, MQTransformer - an improvement of MQCNN - has shown the state-of-the-art performance in probabilistic demand forecasting. In this paper, we consider incorporating cross-entity information to enhance model performance by adding a cross-entity attention mechanism along with a retrieval mechanism to select which entities to attend over. We demonstrate how our new neural architecture, MQRetNN, leverages the encoded contexts from a pretrained baseline model on the entire population to improve forecasting accuracy. Using MQCNN as the baseline model (due to computational constraints, we do not use MQTransformer), we first show on a small demand forecasting dataset that it is possible to achieve ~3% improvement in test loss by adding a cross-entity attention mechanism where each entity attends to all others in the population. We then evaluate the model with our proposed retrieval methods - as a means of approximating an attention over a large population - on a large-scale demand forecasting application with over 2 million products and observe ~1% performance gain over the MQCNN baseline.
Forward citations
Cited by 3 Pith papers
-
Channel-wise Retrieval for Multivariate Time Series Forecasting
CRAFT improves multivariate time series forecasting accuracy by performing independent channel-wise retrieval via time-domain sparse pruning followed by frequency-domain spectral ranking.
-
Channel-wise Retrieval for Multivariate Time Series Forecasting
Channel-wise retrieval with time-domain pruning and spectral ranking improves multivariate time series forecasting over channel-agnostic retrieval baselines on seven public benchmarks.
-
TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting
TAT, a transformer with temporal-alignment attention and posterior calibration, improves peak demand forecast accuracy by up to 30% on proprietary e-commerce data.
Discussion (0). Sign in to comment.