现阶段，Canvas的确能做到让普通用户也能0代码通过机器学习从已有数据分析生成可用的预测模型。但最终能否获取有价值的洞察，预测是否准确，仍会受很多因素的影响：比如输入数据的质量、用户自身的统计学知识和分析能力等等。

从普通业务人员到真正的业务分析师，工具只是我们强大的助手，正如Amazon SageMaker Canvas 并非智者本身而是其引路人。

[1] https://www.oracle.com/cn/business-analytics/what-is-business-analytics/

[2] https://www.kaggle.com/competitions/store-sales-time-series-forecasting/data

[3] https://docs.aws.amazon.com/sagemaker/latest/dg/canvas-make-time-series-forecast.html

[4] https://aws.amazon.com/cn/blogs/china/measuring-forecast-model-accuracy-to-optimize-your-business-objectives-with-amazon-forecast/

[5] https://help.tableau.com/current/pro/desktop/zh-cn/explain_data_basics.htm