The quest for a fair TimeGPT benchmark
At the end of yesterday's #TimeGPT for mobility post, we concluded that TimeGPT's trainingset probably included a copy of the popular BikeNYC timeseries dataset and that, therefore, we were not looking at a fair comparison ...
http://anitagraser.com/2025/03/29/the-quest-for-a-fair-timegpt-benchmark/
#TimeGPT for #mobility: Can foundation models outperform classic machine learning models for flow predictions?
tldr; Maybe. Preliminary results certainly are impressive.
#MobilityDataScience #gischat #urbanmobility #geoai #foundationmodels
tldr; Maybe. Preliminary results certainly are impressive. Introduction Crowd and flow predictions have been very popular topics in mobility data science. Traditional forecasting methods rely on cl…
This post is a first look at Nixtla’s TimeGPT generative, pre-trained transformer for time series forecasting using the nixtlar R package. As described in Garza et al. (2021), TimeGPT is a Transformer-based time series model with self-atten...
[Перевод] Прогнозируем временные данные с TimeGPT
Прогнозирование временных рядов играет ключевую роль в самых разных отраслях: от предсказания тенденций на фондовом рынке до оптимизации цепочек поставок и управления запасами. Однако традиционные модели, такие как ARIMA , экспоненциальное сглаживание (ETS) , Prophet , а также современные подходы глубокого обучения — например, LSTM и архитектуры на базе трансформеров — сталкиваются с рядом проблем.
https://habr.com/ru/companies/bothub/articles/875738/
#ИИ #AI #прогнозирование #ARIMA #ETS #Prophet #TimeGPT #файнтюнинг
Anita Graser 🇪🇺🇺🇦🇬🇪
Harald Klinke
Habr
GripNews