{"uid":"cap_CsQUF0XHE8z_LAzeQnms6","slug":"hubvibe-bigquery-time-series-forecasting-f6974d3c","name":"HubVibe BigQuery Time Series Forecasting","description":"Time-series forecasting: forecast any BigQuery table with Google's pretrained TimesFM model (AI.FORECAST), nothing to train. Point it at the table, timestamp column and value column and get forecast rows with bounds for the horizon you set, per series with id_cols. Use it for sales, traffic, demand or metric forecasts. Input: table, timestamp_col, data_col; optional horizon, id_cols.","url":"https://hubvibe-io.com/work/data/forecast?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"table":{"type":"string"},"horizon":{"type":"integer"},"id_cols":{"type":"array","items":{"type":"string"}},"data_col":{"type":"string"},"language":{"type":"string","pattern":"^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$","maxLength":35},"max_scan_gib":{"type":"number"},"timestamp_col":{"type":"string"}}},"responseSchema":{"type":"json","example":{"result":{"rows":[{"state_name":"Texas","forecast_value":"8631745.2","confidence_level":"0.95","forecast_timestamp":"2023-03-24 00:00:00"}],"table":"bigquery-public-data.covid19_nyt.us_states","columns":["state_name","forecast_timestamp","forecast_value","confidence_level","prediction_interval_lower_bound","prediction_interval_upper_bound","ai_forecast_status"],"horizon":10,"data_col":"confirmed_cases","row_count":10,"gib_processed":0.012,"timestamp_col":"date"},"status":"ok","worker":"data.forecast","price_usd":10,"provenance":{"steps":[{"ms":640,"ok":true,"step":"forecast","provider":"bigquery"}],"attempts":1,"elapsed_ms":660,"providers_used":["bigquery"]},"receipt_id":"rcpt_9f1c2b3a4d5e6f70","receipt_url":"/work/receipts/rcpt_9f1c2b3a4d5e6f70"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"10","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$10/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"10","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"10","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_CzcGnx6RjuVgXLnH7Mh7i","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"10","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Forecast future values of a BigQuery time series using Google's pretrained TimesFM model (AI.FORECAST) without requiring any model training","exampleAgentPrompt":"Forecast the next 14 periods of my BigQuery table `myproject.analytics.daily_sales`, using `sale_date` as the timestamp column and `revenue` as the data column.","exampleUseCases":[{"title":"Retail demand forecasting from BigQuery","prompt":"I have sales data in `acme-corp.warehouse.orders` with a `order_date` timestamp column and `units_sold` value column — can you forecast the next 30 periods so I can plan inventory?"},{"title":"Multi-product revenue trend projection","prompt":"My BigQuery table `biz.reporting.monthly_revenue` has a `month` timestamp column, `revenue` value column, and a `product_id` column for different products — forecast the next 12 periods for all products separately."},{"title":"Website traffic prediction for capacity planning","prompt":"Can you forecast the next 7 periods of traffic in my BigQuery table `infra.monitoring.page_views`, using `recorded_at` as the timestamp and `visit_count` as the value, so I know when to scale up?"}],"resultDescription":"Returns forecasted time series values for the requested horizon periods beyond the last observed data point in the BigQuery table. For multi-series forecasts (when id_cols are specified), returns separate predictions per series identifier. Output includes projected data point values aligned to the cadence of the source data.","failureModes":["Invalid BigQuery table reference (project.dataset.table format required)","Table not accessible or permissions denied","Timestamp or value column name not found in schema","Scan size exceeds max_scan_gib limit","Insufficient historical data in the table to generate a reliable forecast","BigQuery AI.FORECAST quota or region restrictions","Horizon value too large for available data"],"whenToPreferThis":"Choose this endpoint when you need to forecast time series data already stored in BigQuery without any model training or ML infrastructure setup. It is ideal for analysts and agents with BigQuery access who want to leverage Google's pretrained TimesFM foundation model via AI.FORECAST. Prefer this over custom ML pipelines when speed and zero-training convenience matter more than fine-tuning. It supports multi-series forecasting in a single call, making it efficient for product, region, or segment-level predictions.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-27T18:47:53.710Z","isFirstParty":false,"canonicalSlug":"hubvibe-bigquery-time-series-forecasting-f6974d3c"}