mlsanityData to 7 Oct 2026

AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Data

arXiv 2310.20280 ↗First posted 31 Oct 2023cs.LG cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

The efficiency of business processes relies on business key performance indicators (Biz-KPIs), that can be negatively impacted by IT failures. Business and IT Observability (BizITObs) data fuses both Biz-KPIs and IT event channels together as multivariate time series data. Forecasting Biz-KPIs in advance can enhance efficiency and revenue through proactive corrective measures. However, BizITObs data generally exhibit both useful and noisy inter-channel interactions between Biz-KPIs and IT events that need to be effectively decoupled. This leads to suboptimal forecasting performance when existing multivariate forecasting models are employed. To address this, we introduce AutoMixer, a time-series Foundation Model (FM) approach, grounded on the novel technique of channel-compressed pretrain and finetune workflows. AutoMixer leverages an AutoEncoder for channel-compressed pretraining and integrates it with the advanced TSMixer model for multivariate time series forecasting. This fusion greatly enhances the potency of TSMixer for accurate forecasts and also generalizes well across several downstream tasks. Through detailed experiments and dashboard analytics, we show AutoMixer's capability to consistently improve the Biz-KPI's forecasting accuracy (by 11-15%) which directly translates to actionable business insights.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 10 of its 20 references that are in the map. First posted on arXiv 31 Oct 2023.

Builds on

10 of 20 references.

References · 10

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  5. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  6. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  7. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  8. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  9. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 748
  10. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 8.

17 papers.

Sort:

By area:

  1. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 120
  2. 2024Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Expertscited by 88
  3. 2025This Time is Different: An Observability Perspective on Time Series Foundation Modelscited by 57
  4. 2025fev-bench: A Realistic Benchmark for Time Series Forecastingcited by 52
  5. 2025Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Modelcited by 21
  6. 2026Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Modelscited by 10
  7. 2026Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modelingcited by 7
  8. 2025TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysiscited by 5
  9. 2026Zero-shot Forecasting by Simulation Alonecited by 4
  10. 2026Into the ORBIT for Time Series: Training Regimes for Foundation Modelscited by 3
  11. 2025Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecastingcited by 2
  12. 2026Adapting Time Series Foundation Models through Data Mixturescited by 2
5 more
  1. 2026Foundation Models and Fine-Tuning: Toward a New Generation of Models for Time Series Forecastingcited by 2
  2. 2026RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Modelscited by 1
  3. 2025Predictability-Aware Compression and Decompression Framework for Multichannel Time Series Data with Latent Seasonalitycited by 0
  4. 2025Mod`eles de Fondation et Ajustement : Vers une Nouvelle G'en'eration de Mod`eles pour la Pr'evision des S'eries Temporellescited by 0
  5. 2026When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasterscited by 0