The correct answer is B. Transform the data into a consistent format. Here's why:
* Context of the Question: The cinema company wants to build a machine learning model to predict customer visit patterns using three years of customer visit data stored in different formats. For effective ML model training, the input data must be in a consistent format.
* Google Cloud Product Relevance:
* To build a robust and accurate ML model, the data used for training needs to be cleaned, pre- processed, and transformed into a consistent format. This process ensures that the model can interpret and learn from the data correctly.
* Google Cloud provides services like Dataflow for data transformation and processing, and Dataprep for data cleaning and preparation. These tools help standardize data formats before feeding it into a machine learning model.
* Why Not Other Options:
* A. Choose an ML model type that can process different formats of input data: Most ML models require data to be in a uniform format; choosing a model that processes multiple formats is not standard practice and can lead to inaccuracies.
* C. Use the last year of data so there are fewer inconsistencies for the model to handle: This would limit the amount of data available for training, reducing the model's accuracy and effectiveness.
* D. Group different format types and train a different model for each group: Training multiple models for different data formats is inefficient and complex compared to transforming the data into a single consistent format.
Google Cloud Digital Leader References:
* Refer to Dataflow and Dataprep documentation for details on data transformation and preparation services in Google Cloud.