BigQuery ML ARIMA_PLUS는 일변량 예측 모델입니다. 통계 모델은 신경망 기반 모델보다 학습 속도가 빠릅니다.
모델 학습을 여러 번 빠르게 반복해야 하거나 다른 모델을 측정하기 위한 경제적인 기준이 필요한 경우 BigQuery ML ARIMA_PLUS 모델을 학습시키는 것이 좋습니다.
Prophet과 마찬가지로 BigQuery ML ARIMA_PLUS는 각 시계열을 트렌드, 계절, 공휴일로 분할하고 이러한 모델의 예측 집계를 사용하여 예측을 생성하려고 시도합니다. 하지만 여러 차이점 중 하나는 BQML ARIMA+가 ARIMA를 사용하여 트렌드 구성요소를 모델링하는 반면 Prophet은 개별 로지스틱 또는 선형 모델을 사용하여 곡선에 맞추려 시도한다는 점입니다.
Google Cloud 는 BigQuery ML ARIMA_PLUS 모델을 학습시키기 위한 파이프라인과 BigQuery ML ARIMA_PLUS 모델에서 일괄 예측을 수행하기 위한 파이프라인을 제공합니다.
두 파이프라인 모두 Google Cloud 파이프라인 구성요소(GCPC)의 Vertex AI Pipelines의 인스턴스입니다.
[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["이해하기 어려움","hardToUnderstand","thumb-down"],["잘못된 정보 또는 샘플 코드","incorrectInformationOrSampleCode","thumb-down"],["필요한 정보/샘플이 없음","missingTheInformationSamplesINeed","thumb-down"],["번역 문제","translationIssue","thumb-down"],["기타","otherDown","thumb-down"]],["최종 업데이트: 2025-09-04(UTC)"],[],[],null,["# Forecasting with ARIMA+\n\n| To see an example of how to train a model with ARIMA+,\n| run the \"Train a BigQuery ML ARIMA_PLUS model using Vertex AI tabular workflows\" notebook in one of the following\n| environments:\n|\n| [Open in Colab](https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/tabular_workflows/bqml_arima_plus.ipynb)\n|\n|\n| \\|\n|\n| [Open in Colab Enterprise](https://console.cloud.google.com/vertex-ai/colab/import/https%3A%2F%2Fraw.githubusercontent.com%2FGoogleCloudPlatform%2Fvertex-ai-samples%2Fmain%2Fnotebooks%2Fofficial%2Ftabular_workflows%2Fbqml_arima_plus.ipynb)\n|\n|\n| \\|\n|\n| [Open\n| in Vertex AI Workbench](https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https%3A%2F%2Fraw.githubusercontent.com%2FGoogleCloudPlatform%2Fvertex-ai-samples%2Fmain%2Fnotebooks%2Fofficial%2Ftabular_workflows%2Fbqml_arima_plus.ipynb)\n|\n|\n| \\|\n|\n| [View on GitHub](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/tabular_workflows/bqml_arima_plus.ipynb)\n\n\n[BigQuery ML ARIMA_PLUS](/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create-time-series) is a univariate forecasting model. As\na statistical model, it is faster to train than a [model based on neural networks](/vertex-ai/docs/tabular-data/forecasting/overview).\nWe recommend training a BigQuery ML ARIMA_PLUS model if you need to\nperform many quick iterations of model training or if you need an inexpensive\nbaseline to measure other models against.\n\nLike [Prophet](/vertex-ai/docs/tabular-data/forecasting-prophet),\nBigQuery ML ARIMA_PLUS attempts to decompose each time series into\ntrends, seasons, and holidays, producing a forecast using the aggregation of\nthese models' inferences. One of the many differences, however, is that\nBQML ARIMA+ uses ARIMA to model the trend component, while Prophet attempts to\nfit a curve using a piecewise logistic or linear model.\n\nGoogle Cloud offers a pipeline for training a BigQuery ML ARIMA_PLUS\nmodel and a pipeline for getting batch inferences from a BigQuery ML ARIMA_PLUS model.\nBoth pipelines are instances of\n[Vertex AI Pipelines](/vertex-ai/docs/pipelines/introduction) from\n[Google Cloud Pipeline Components](/vertex-ai/docs/pipelines/components-introduction) (GCPC).\n\nWhat's next\n-----------\n\n- Learn more about [BigQuery ML ARIMA_PLUS](/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create-time-series).\n- Learn about [the service accounts used by this workflow](/vertex-ai/docs/tabular-data/tabular-workflows/service-accounts#arima)."]]