Pith. sign in

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

arxiv 2207.10517 v2 pith:R34ZFOYV submitted 2022-07-21 cs.LG cs.AI

classification cs.LGcs.AI
keywords forecastingdemandmodelattentionbaselinecross-entitymechanismmqcnn
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Channel-wise Retrieval for Multivariate Time Series Forecasting

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    CRAFT improves multivariate time series forecasting accuracy by performing independent channel-wise retrieval via time-domain sparse pruning followed by frequency-domain spectral ranking.

  2. Channel-wise Retrieval for Multivariate Time Series Forecasting

    cs.LG 2026-04 conditional novelty 6.0 of 10

    Channel-wise retrieval with time-domain pruning and spectral ranking improves multivariate time series forecasting over channel-agnostic retrieval baselines on seven public benchmarks.

  3. TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting

    cs.LG 2025-07 conditional novelty 5.0 of 10

    TAT, a transformer with temporal-alignment attention and posterior calibration, improves peak demand forecast accuracy by up to 30% on proprietary e-commerce data.

Pith tools