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


  • Santosh Palaskar Indian Institute of Technology Bombay
  • Vijay Ekambaram IBM Research
  • Arindam Jati IBM Research
  • Neelamadhav Gantayat IBM Research
  • Avirup Saha IBM Research
  • Seema Nagar IBM Research
  • Nam H. Nguyen IBM Research
  • Pankaj Dayama IBM, Research
  • Renuka Sindhgatta IBM Research
  • Prateeti Mohapatra IBM Research
  • Harshit Kumar IBM Research
  • Jayant Kalagnanam IBM Research
  • Nandyala Hemachandra Indian Institute of Technology Bombay
  • Narayan Rangaraj IIT Bombay



Deep Learning and Neural Networks , Analytics and Data Science , Multidisciplinary Topics and Applications , Track: Emerging Applications, Transfer Learning


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.




How to Cite

Palaskar, S., Ekambaram, V., Jati, A., Gantayat, N., Saha, A., Nagar, S., Nguyen, N. H., Dayama, P., Sindhgatta, R., Mohapatra, P., Kumar, H., Kalagnanam, J., Hemachandra, N., & Rangaraj, N. (2024). AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Data. Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 22962-22968.