DeepAR

Amazon’s new Time-Series Forecasting modelCreated with DALLE What is the most enjoyable thing when you read a new paper? For me, this is the following:Imagine a popular model suddenly getting upgraded — with just a few elegant tweaks.Three years after DeepAR , Amazon engineers published its revamped version, known as Deep GPVAR (Deep Gaussian-Process Vector Auto-regressive).This is a much-improved model of the original version. Plus, it is open-source. In this article, we discuss:How Deep GPVAR works in depth.How DeepAR…

Amazon’s autoregressive deep networkCreated with Stable Diffusion A few years ago, time-series models worked on a single sequence only.Hence, if we had multiple time-series, one option was to create one model per sequence. Or, if we could “tabularize” our data, we could apply the gradient-boosted tree models — which work very well even today.The first model that could natively work on multiple time-series was DeepAR, an autoregressive recurrent network developed by Amazon.In this article, we will see how DeepAR works…

Improve your KPI by 15% with 3X faster, free & interpretable modelPhoto by Victoire Joncheray on UnsplashIf you’re reading this article, you either consider using the Amazon SageMaker DeepAR algorithm for your multiple time series dataset, or you’re already “stuck” with one — and are not sure how to improve it any further.How your dataset probably looks like. Airtable (data by the author)Before delving into the neety grity technicals, you should contemplate on these:DeepAR prosNo Data Science expertise needed — If you…