This reviewer's identity has been verified by our review moderation team. They have asked not to show their name, job title, or picture.
Most time-series project die an early death due to heavy burden of sustaining a good quality forecasting model. TimeGPT provides a great way to maintain very high-quality forecasts with an easy to use API. The zero-shot forecasts are already quite good compared to the other classical methods for time-series analysis. Fine-tuning takes your relevant accuracy metrics to the next level.
Combining covariates and exogenous variables is also easy and combines time-series trends with SME like inputs that influence future outcomes and helps make your predictions more believable. Review collected by and hosted on G2.com.
High license cost for the paid version. The payg version is usually far behind the latest from Nixtla in terms of features. Review collected by and hosted on G2.com.
Validated through a business email account
Organic review. This review was written entirely without invitation or incentive from G2, a seller, or an affiliate.
