You are an AI engineer with an apparel retail company. The sales team has observed seasonal sales patterns over the past 5-6 years. The sales team analyzes and visualizes the weekly sales data stored

Question

Options

• AUpload the files into Cloud Storage. Use Python to preprocess and load the tabular data into
• BUpload the files into Cloud Storage. Use Python to preprocess and load the tabular data into
• CLoad the files into BigQuery. Preprocess data by using BigQuery SQL. Connect BigQuery to
• DCreate a custom conversational application using Vertex AI Agent Builder. Include code that

• A
  83% (24)
• B
  3% (1)
• C
  10% (3)
• D
  3% (1)

Explanation

The task is time series forecasting (weekly sales, seasonal patterns over 5–6 years) with an emphasis on efficiency. Option A involves uploading CSVs to Cloud Storage, preprocessing with Python, loading into BigQuery, and then using a managed forecasting service-most likely Vertex AI AutoML Forecasting or BigQuery ML's ARIMA_PLUS model, both of which handle seasonality automatically with minimal custom modeling code. Option D (Vertex AI Agent Builder conversational app) is entirely inappropriate for structured time series forecasting. Options B and C have similar starts but differ in the modeling endpoint; A is selected as the most efficient full pipeline. AutoML Forecasting or BigQuery ML time series models are the efficient managed path for seasonal sales forecasting without building custom models.

No community discussion yet for this question.