# Inverted Transformers for Time Series Forecasting

**URL:** <https://discourse.numenta.org/t/inverted-transformers-for-time-series-forecasting/11092>\
**Category:** Lounge\
**Created:** [November 14, 2023, 11:12am UTC](https://discourse.numenta.org/t/inverted-transformers-for-time-series-forecasting/11092 "2023-11-14T11:12:37Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![cezar\_t](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/cezar_t/32/4451_2.png) [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\
**Post date:** [November 14, 2023, 11:12am UTC](https://discourse.numenta.org/t/inverted-transformers-for-time-series-forecasting/11092/1 "2023-11-14T11:12:37Z")

</div>

No, inverted doesn’t refer at reciting stuff backwards. It seems more like an _encoding trick_ of time series data which renders transformers significantly more effective at predicting multivariate time series

> **[iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://arxiv.org/abs/2310.06625)**
>
> The recent boom of linear forecasting models questions the ongoing passion for architectural modifications of Transformer-based forecasters. These forecasters leverage Transformers to model the global dependencies over temporal tokens of time series,...